Category: 3. Business

Journal of Medical Internet Research

The application of large language models (LLMs) within the medical domain is undergoing rapid growth [,]. Key areas of investigation include assisted diagnosis [] and the structured representation of electronic health records []. These models exhibit considerable potential, with preliminary findings from research and practical implementations showing promising results. LLMs through pretraining and fine-tuning on extensive datasets containing medical literature, clinical records, and biomedical knowledge bases, leverage deep learning methodologies to develop rich linguistic representations and demonstrate robust contextual understanding and knowledge integration []. This results in significantly enhanced performance compared with traditional language processing tools across natural language understanding, pattern recognition, and correlation analysis, with notable advantages in processing intricate medical data and facilitating cross-domain knowledge transfer []. While the pursuit of enhanced model performance remains crucial, ensuring robust protection of patient privacy and data security remains a paramount concern and a fundamental requirement for the responsible and sustainable advancement of LLM applications in health care. This presents a complex challenge that necessitates both technical and regulatory solutions [-].

A substantial portion of current research on LLMs for health care applications uses publicly available resources [], such as the Medical Information Mart for Intensive Care-IV []. However, some studies are conducted using internal patient health information (PHI) repositories, which often contain highly sensitive personally identifiable information (PII) [], including patient names, medical record numbers, age, zip code, admission date, and so on. This practice necessitates robust data governance frameworks to ensure patient privacy and data security. In conventional approaches to developing computer models using patient data, researchers typically processed and trained data within local or strictly regulated environments. This practice inherently reduced the risk of sensitive data compromise during transmission and storage [,]. However, deploying LLMs on the cloud often requires uploading vast amounts of raw medical data directly to remote servers. These servers may be distributed across different regions and are frequently not entirely under the control of health care institutions or researchers [,]. Beyond these conventional risks, LLMs introduce additional privacy concerns [] due to their generative nature; they may inadvertently reproduce sensitive information learned during training, and their large scale and complexity expose them to attacks such as model inversion or prompt injection. Together, these factors make the protection of medical data in LLM deployment especially challenging. Recent studies have highlighted concrete privacy threats associated with LLM use: fine-tuning can significantly increase PII memorization and vulnerability to leakage attacks, especially when tuning specific layers of the model []; novel mitigation strategies like “Whispered Tuning,” which combine PII redaction, differential privacy, and output filtering, can markedly reduce leakage while preserving performance []; and beyond memorization, pretrained LLMs can infer personal attributes (eg, location, income, and gender) from seemingly innocuous text with high accuracy []. Consequently, data transmission and storage processes may encounter heightened risks of security vulnerabilities and unauthorized access. Whether through misuse by internal personnel or external cyberattacks, PHI is at risk of improper use or malicious disclosure [].

Therefore, reconciling the potential of LLMs to enhance health care quality and efficiency with the imperative to protect patient privacy represents a significant challenge requiring careful consideration. The regulatory oversight of LLMs processing PHI is governed by a complex patchwork of national and international privacy laws, including the General Data Protection Regulation in the European Union and the Health Insurance Portability and Accountability Act (HIPAA) in the United States []. Besides, Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD)-LLM [] is an extension of the TRIPOD+AI statement, addressing the unique challenges of LLMs in biomedical and health care applications. There is a growing consensus within the academic community regarding the paramount importance of patient privacy protection in LLM research, with numerous concerns and queries being raised concerning the potential risks to sensitive data [,]. A range of privacy-preserving techniques is being widely considered and adopted within the health care domain to ensure data security and regulatory compliance. These include established methods such as deidentification [,], differential privacy [], federated learning [], and homomorphic encryption [,].

This leads us to our core research question: What measures are being used to protect patient privacy in the PHI-LLMs in the health care field, and are these measures sufficient? Although there are some systematic reviews or scope reviews of LLM research in health care, no scoping review has been published on this critical issue. The primary objective of this study is to conduct a scoping review of the existing literature on PHI-LLMs in health care, evaluate the adequacy of current approaches, and identify areas in need of improvement to ensure robust patient privacy protection.

Study Design

This scoping review was guided by the framework for scoping studies by Arksey and O’Malley []. Besides, the study reporting followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR; checklist provided in ) []. We focused on the following three research questions: (1) What studies on the development and application of LLMs using PHI currently exist within the health care domain? (2) What patient privacy considerations are addressed in existing PHI-LLMs research, and are these measures sufficient? (3) How can future research on the development and application of LLMs using PHI better protect patient privacy?

Eligibility Criteria

The inclusion and exclusion criteria for studies are shown in .

Textbox 1. Inclusion and exclusion criteria.

Inclusion criteria

Studies were included if they focused on the development and application of large language models within health care using personal health information, encompassing activities such as model construction, fine-tuning, optimization, testing, and performance comparison.
Eligible literature comprised original research articles written in English.

Exclusion criteria

Studies used publicly available datasets, under the assumption that such data have been adequately deidentified.
Studies that were not reviews, abstracts, incomplete reports, or preprints were excluded from the review due to the lack of rigorous peer review.

Data Sources, Search Strategy, and Study Selection

We searched PubMed and Embase for studies published between January 1, 2022, and July 20, 2025. This timeframe was chosen to coincide with the release and rapid adoption of advanced LLMs (eg, GPT-3.5 and ChatGPT) and the subsequent surge of their applications in health care. Earlier studies (published before 2022), which primarily investigated transformer-based or nongenerative models, were excluded as they fell outside the scope of this review. The search strategies were drafted by ZXY and further refined through team discussion. The final search strategy can be found in . The final search results were exported into EndNote X9, and duplicates were removed by a library technician.

First, the titles and abstracts of identified studies were independently screened by 2 researchers (ZXY and LSY) based on the inclusion and exclusion criteria. Any disagreements between the reviewers were resolved through group discussions involving at least 2 researchers to ensure consensus and maintain the integrity of the selection process. The full-text review was also conducted by 2 researchers (ZXY and LSY) independently, with conflicts resolved through whole-group discussion.

Data Extraction

The data extraction form was initially drafted by ZXY based on the study objectives and research questions. Following the draft, the form was refined through group discussions to develop a preliminary extraction template. To ensure consistency in the definitions and extraction criteria, 10 articles were randomly selected for a pilot extraction. Feedback from this pilot phase was used to finalize the extraction form. Subsequently, ZXY and LSY independently extracted data from the included studies. Any conflicts or discrepancies encountered during the extraction process were resolved through comprehensive group discussions involving all researchers to maintain the integrity and consistency of the data extraction.

The extracted data encompassed three main categories:

General characteristics of included studies: this included the first author’s name, publication year, country, the name and type of the LLMs used or developed, the disease domain as classified by the World Health Organization, and the type of tasks based on the classification outlined in the previous article [].
General characteristics of clinical design: this section captured the sample size, the number of centers, the type of data used, the data collection method, the reporting statement they followed, and whether the study protocol was registered or not. The name of the LLM used or developed, the research objective, and the deployment type.
Patient privacy protection considerations: this part focused on the data source, the purpose of using PHI, whether the study underwent ethical review or approval, the declaration of data availability, whether patient consent was obtained, and the PHI protection techniques used.

All extracts are based on reports from the included study itself.

Data Analysis

Descriptive analyses were performed to summarize the characteristics of the included studies. Categorical variables were summarized as frequencies and percentages. Sample size was further categorized into predefined ranges and presented as frequencies and percentages, while other continuous or count-based variables were directly summarized as reported. All results were presented in tables or figures according to the main domains of study characteristics, data characteristics, and privacy protection measures.

Patient and Public Involvement

As this was a scoping review of previously published research, no patients or the public were involved in the design of this study.

Selection of Sources of Evidence

After removing duplicates, a total of 6174 citations were identified through searches of electronic databases and references in review articles. Based on their titles and abstracts, 3181 full-text articles were retrieved and assessed for eligibility. Of these, 2993 were excluded for the following reasons: 4 were not written in English, 48 were preprint papers, 126 were unrelated to LLM research, 1387 were reviews, comments, or letters, 38 were protocols, and 1390 did not involve relevant patient data. Following the eligibility assessment, a total of 2717 records were excluded for the following reasons: 647 used only public databases or previously published cases, 439 simulated clinical scenarios or patients rather than using real-world data, 1587 focused on medical knowledge quizzes or examinations, and 44 represented secondary analyses. Ultimately, 464 studies were deemed eligible for this review () []. The specific references included in the analysis are listed in the .

‎

Figure 1. PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) study selection diagram.

General Characteristics of the Included Studies

To provide an overview of the studies included in this review, we summarize their general characteristics in . This review encompasses studies published between January 1, 2022, and July 20, 2025. Of the 464 studies included in this review, the majority were published in 2025 (n=256, 55.2%), with a substantial proportion appearing in 2024 (n=188, 40.5%). In contrast, only a small number of studies were published in 2023 (19/464, 4.1%) and 2022 (1/464, 0.2%). This temporal distribution underscores the rapid and recent surge of research on LLM applications in health care, with most evidence emerging within the past 2 years. Based on the institutions of the first authors, the largest proportion of studies originated from the United States (153/464, 33.0%), followed by China (94/464, 20.3%) and Germany (37/464, 8.0%). Moderate contributions were observed from Turkey (31/464, 6.7%), Italy (17/464, 3.7%), Israel (13/464, 2.8%), South Korea (12/464, 2.6%), and the United Kingdom (12/464, 2.6%). Studies from other countries collectively accounted for 20.5% (n=95).

Table 1. General characteristics of included studies.

Characteristic				Values
Publication year, n (%)
	2025		256 (55.2)
	2024		188 (40.5)
	2023		19 (4.1)
	2022		1 (0.2)
Country, n (%)
	United States		153 (33.0)
	China		94 (20.3)
	Germany		37 (8.0)
	Turkey		31 (6.7)
	Italy		17 (3.7)
	Israel		13 (2.8)
	South Korea		12 (2.6)
	United Kingdom		12 (2.6)
	Other countries^a		95 (20.5)
Model type, n (%)
	Existing model		356 (76.7)
	Fine-tuning model + existing model		49 (10.6)
	Fine-tuning model		40 (8.6)
	Self-developed model		17 (3.7)
	Self-developed model + existing model		2 (0.4)
Location of the large language model, n (%)
	Cloud deployment		72 (15.5)
	Local deployment		70 (15.1)
	External cloud service		69 (14.9)
	Others^b		8 (1.7)
	Cannot judge		57 (12.3)
	Not report		188 (40.5)
Task type, n (%)
	Making diagnoses		134 (28.9)
	Clinical note-taking		62 (13.4)
	Making treatment recommendations		45 (9.7)
	Generating medical reports		43 (9.3)
	Biomedical data mining		38 (8.2)
	Prognostic predictive model		22 (4.7)
	Communicating with patients		20 (4.3)
	Making diagnoses + Making treatment recommendations		19 (4.1)
	Other tasks^c		81 (17.5)
Sample size^d, n (%)
	Patients (n=342, 73.7%)
		<100	125 (36.5)
		100-1000	161 (47.1)
		1000-10,000	35 (10.2)
		≥10,000	19 (5.6)
		Not report	2 (0.6)
	Token (n=16, 3.4%)
		100-1000	10 (62.5)
		1000-10,000	3 (18.8)
		≥10,000	2 (12.5)
		Not report	1 (6.3)
	Notes (n=94, 20.3%)
		<100	12 (12.8)
		100-1000	19 (20.2)
		1000-10,000	23 (24.5)
		≥10,000	38 (40.4)
		Not report	2 (2.1)
	Images (n=12, 2.6%)
		<100	2 (16.7)
		100-1000	7 (58.3)
		1000-10,000	1 (8.3)
		≥10,000	2 (16.7)
Number of centers^e, n (%)
	1		377 (81.3)
	2		41 (8.8)
	3		16 (3.4)
	4		7 (1.5)
	≥5		20 (4.3)
	Not report		3 (0.6)
Summarize the large language models used in the research, n (%)
	ChatGPT		341 (73.5)
	Llama		74 (15.9)
	Mistral		27 (5.8)
	Flan		13 (2.8)
	Claude		19 (4.1)
	Gemini		32 (6.9)
	Gemma		9 (1.9)
	GLM		9 (1.9)
	Deepseek		6 (1.3)
	Qwen		13 (2.8)
	Fine-tuning		49 (10.6)
	Others		73 (15.7)
Type of data, n (%)
	Text		366 (78.9)
	Text + Image		35 (7.5)
	Text + Audio		4 (0.9)
	Image		56 (12.1)
	Audio		2 (0.4)
	Text + Image + Audio		1 (0.2)
Data collection method, n (%)
	Retrospective		409 (88.1)
	Prospective		53 (11.4)
	Prospective + retrospective		2 (0.4)
Follow the statement, n (%)
	Not report		435 (93.8)
	STROBE^f		17 (3.7)
	STARD^g		3 (0.6)
	TRIPOD^h		7 (1.5)
	CLAIMⁱ		2 (0.4)
Registered, n (%)
	No		451 (97.2)
	Yes		13 (2.8)

^aOther countries: Japan (n=11), Australia (n=10), France (n=9), Spain (n=9), Canada (n=6), Switzerland (n=5), India (n=5), Singapore (n=4), Belgium (n=3), Brazil (n=3), Croatia (n=3), the Netherlands (n=3), Pakistan (n=3), Saudi Arabia (n=3), Ireland (n=2), Mexico (n=2), Portugal (n=2), Romania (n=2), Thailand (n=2), Burkina Faso (n=1), Finland (n=1), Iran (n=1), Jordan (n=1), Poland (n=1), Ukraine (n=1), United Arab Emirates (n=1), and Vietnam (n=1).

^bOther location of LLMs: local deployment + cloud deployment (n=5); local deployment + external cloud service (n=2); cloud deployment + external cloud service (n=1).

^cOther tasks: synthesizing data for research (n=15), translation (n=12), triaging patients (n=11), conducting medical research (n=7), making diagnoses + triaging patients + Making treatment recommendations (n=5), making diagnoses + generating medical reports (n=4), generating billing codes (n=3), writing prescriptions (n=3), making diagnoses + triaging patients (n=2), making diagnoses + biomedical data mining (n=2); educating patients (n=2), making treatment recommendations + triaging patients (n=2), communicating with patients + making treatment recommendations (n=2), clinical note-taking + making treatment recommendations (n=2); enhancing medical knowledge (n=1), educating patients + making treatment recommendations + making diagnoses (n=1), communicating with patients + making diagnoses + making treatment recommendations (n=1), triaging patients + prognostic (n=1), generating medical reports + making treatment recommendations (n=1), generating medical reports + prognostic (n=1), clinical note-taking + generating medical reports (n=1), clinical note-taking + prognostic (n=1), and clinical note-taking + translation (n=1).

^dSample size was defined according to the primary data modality: number of patients (clinical studies), number of images (imaging studies), or number of clinical notes/documents (text-based studies), number of tokens (referring to the unit of original studies).

^eReferring to the number of clinical sites contributing patient data.

^fSTROBE: Strengthening the Reporting of Observational Studies in Epidemiology.

^gSTARD: Standards for Reporting of Diagnostic Accuracy.

^hTRIPOD: Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis.

ⁱCLAIM: Checklist for Artificial Intelligence in Medical Imaging.

With respect to model type, 356 (76.7%) studies used existing models, 49 (10.6%) studies combined fine-tuning with existing models, 40 (8.6%) studies applied fine-tuning alone, 17 (3.7%) studies developed their own models, and 2 (0.4%) studies reported using both self-developed and existing models. Regarding the location of LLM deployment, 72 (15.5%) studies reported cloud deployment, 70 (15.1%) studies reported local deployment, and 69 (14.9%) studies reported the use of external cloud services. Eight (1.7%) studies used other deployment approaches, 57 (12.3%) studies could not be judged from the report, and 188 (40.5%) studies did not provide deployment information.

A total of 134 (28.9%) studies focused on making diagnoses, 62 (13.4%) studies focused on clinical note-taking, 45 (9.7%) studies focused on making treatment recommendations, 43 (9.3%) studies focused on generating medical reports, and 38 (8.2%) studies focused on biomedical data mining. Prognostic predictive model tasks were examined in 22 (4.7%) studies, and communication with patients in 20 (4.3%) studies. In addition, 19 (4.1%) studies combined diagnostic and treatment recommendation tasks, while other tasks were reported in 81 (17.5%) studies.

Regarding sample size, the distribution was varied: 125 (36.5%) studies enrolled fewer than 100 patients, 161 (47.1%) studies included 100-1000 patients, 35 (10.2%) studies included 1000-10,000 patients, 19 (5.6%) studies included more than 10,000 patients, and 2 (0.6%) studies did not report sample size. For token-based datasets (n=16), 10 (62.5%) studies used 100-1000 tokens, 3 (18.8%) studies used 1000-10,000, 2 (12.5%) studies used more than 10,000, and 1 (6.3%) study did not report. Regarding note-based datasets (n=94), 12 (12.8%) studies analyzed fewer than 100 notes, 19 (20.2%) studies used 100-1000, 23 (24.5%) studies used 1000-10,000, 38 (40.4%) studies used more than 10,000, and 2 (2.1%) studies did not report. For image-based datasets (n=12), 2 (16.7%) studies included fewer than 100 images, 7 (58.3%) studies included 100-1000, 1 (8.3%) studies included 1000-10,000, and 2 (16.7%) studies included more than 10,000.

Regarding the number of centers, 377 (81.3%) studies were conducted in a single center, 41 (8.8%) studies were conducted in 2 centers, 16 (3.4%) studies were conducted in 3 centers, and 7 (1.5%) studies were conducted in 4 centers. Twenty (4.3%) studies involved 5 or more centers, while 3 (0.6%) studies did not report this information. As for LLMs used in the research, ChatGPT was the most frequently used model, accounting for 341 (73.5%) studies. This was followed by 74 (15.9%) studies used Llama, 32 (6.9%) studies used Gemini, 27 (5.8%) studies used Mistral, 19 (4.1%) studies used Claude, and 13 (2.8%) studies used Qwen. Additionally, 49 (10.6%) studies applied fine-tuning techniques, while 73 (15.7%) studies reported using other models not specifically listed. Regarding data type, 366 (78.9%) studies used text; 56 (12.1%) studies used image data; 35 (7.5%) studies combined text and image; 4 (0.9%) studies combined text and audio; 2 (0.4%) studies used audio only; and 1 (0.2%) study combined text, image, and audio. With respect to data collection method, 409 studies (88.1%) were retrospective, 53 (11.4%) studies were prospective, and 2 (0.4%) studies combined both prospective and retrospective approaches.

With respect to reporting standards, 435 (93.8%) studies did not specify adherence to any guideline/statement, while 17 (3.7%) studies followed Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement, 3 (0.6%) studies followed the Standards for Reporting of Diagnostic Accuracy (STARD) statement, 7 (1.5%) studies followed TRIPOD statement, and 2 (0.4%) studies followed Checklist for Artificial Intelligence in Medical Imaging. Regarding study registration, 451 (97.2%) studies were not registered, and only 13 (2.8%) studies reported registration.

The Sankey diagram () shows that the most frequent disease-task pairs included tumors with making diagnoses (n=35), tumors with making treatment recommendations (n=23), and tumors with clinical note-taking (n=16). In addition, studies categorized as “not special” also frequently addressed making diagnoses (n=24) and clinical note-taking (n=15). Other notable pairs included musculoskeletal disorders with making diagnoses (n=17), neurological disorders with making diagnoses (n=13), and circulatory diseases with making diagnoses (n=11). Tasks such as generating medical reports and biomedical data mining were also commonly associated with tumors and “not special” categories. The summary table could be found in .

**Figure 2.** Sankey diagram of disease categories and task types.

Characteristics of Privacy Protection

outlines the characteristics of privacy protection measures implemented in the included studies. Regarding ethical oversight, 419 (90.3%) studies reported approval from an ethics committee, whereas 45 (9.7%) studies did not. With respect to patient consent, 224 (48.3%) studies reported a waiver of informed consent, 92 (19.8%) studies indicated that informed consent had been obtained, and 148 (31.9%) studies did not report consent information. For data availability, 203 (43.8%) studies did not provide a statement, 160 (34.5%) studies declared that data were available from the corresponding author upon reasonable request, 66 (14.2%) studies stated that data were not available, and 35 (7.5%) studies made data publicly accessible.

Table 2. Characteristics of privacy protection. Our categorization of privacy protection methods is based on terminology as reported by the original studies. However, the definitions of “de-identification” and “anonymization” vary across contexts; thus, the risk implications should be interpreted with caution.

Characteristics			Values, n (%)
Ethical review
	Yes		419 (90.3)
	No		45 (9.7)
Patient consent
	Waiver of informed consent		224 (48.3)
	Not report		148 (31.9)
	Informed consent has been obtained		92 (19.8)
Data availability declaration
	Not report		203 (43.8)
	Corresponding author on reasonable request		160 (34.5)
	Not open		66 (14.2)
	Public		35 (7.5)
Privacy protection technology
	Not report		178 (38.4)
	Deidentification		158 (34.1)
		Cannot judge from report	116 (73.4)
		Based on manual	17 (10.8)
		Based on rule matching	13 (8.2)
		Others^a	12 (7.6)
	Anonymization		91 (19.6)
	Deidentification+Anonymization		23 (5.0)
	Others^b		14 (3.0)
Is there a statement to remove any personally identifiable information?
	No		363 (78.2)
	Yes		101 (21.8)
Were direct identifiers or indirect identifiers removed?
	Direct identifiers		166 (35.8)
	Indirect identifiers		9 (1.9)
	Cannot judge		107 (23.1)
	Not report		182 (39.2)
Whether the degree of deidentification is assessed?
	No		458 (98.7)
	Yes		6 (1.3)
Reidentification protection technology used?
	No		455 (98.1)
	Yes		9 (1.9)
Declaration of compliance with safety standards
	Health Insurance Portability and Accountability Act		44 (9.5)
	General Data Protection Regulation		6 (1.3)
	Both		2 (0.4)
	Not report		412 (88.8)

^aBased on rule matching + machine learning + deep learning (n=3), based on LLMs (n=2), based on rule matching + manual (n=2), based on rule matching + machine learning (n=1), based on synthetic data (n=1), based on postprocessing (n=1), based on machine learning (n=1), and based on deep learning+ postprocessing (n=1).

^bData hosting (n=5), anonymization + data hosting (n=3), federated learning (n=1), anonymization + data hosting + homomorphic encryption (n=1), anonymization + homomorphic encryption (n=1), deidentification + data hosting (n=1), data augmentation (likely referred to synthetic data generation; n=1), and homomorphic encryption (n=1).

When examining privacy protection technologies, 178 (38.4%) studies did not report the methods used, while 158 (34.1%) studies applied deidentification, 91 (19.6%) studies used anonymization, 23 (5.0%) studies reported combining both, and 14 (3.0%) studies used other technologies. Among those providing more detail about deidentification, 17 (10.8%) studies used manual methods, 13 (8.2%) studies applied rule-based matching, 12 (7.6%) studies reported other approaches, and 116 (73.4%) studies cannot be judged from the reports.

Concerning statements on the removal of personally identifiable information, 363 (78.2%) studies did not provide such a statement, while 101 (21.8%) studies explicitly reported it. About the type of identifiers removed, 166 (35.8%) studies specified the removal of direct identifiers, 9 (1.9%) studies reported the removal of indirect identifiers, 107 (23.1%) studies could not be judged from the report, and 182 (39.2%) studies did not provide this information. Regarding assessment of the degree of deidentification, 458 (98.7%) studies did not report such an assessment, while 6 (1.3%) studies did. Concerning reidentification protection technologies, 455 (98.1%) studies did not use them, and 9 (1.9%) studies reported their use. With respect to compliance with safety standards, 44 (9.5%) studies declared adherence to HIPAA, 6 (1.3%) studies to the General Data Protection Regulation, and 2 (0.4%) studies to both, whereas 412 (88.8%) studies did not provide such information.

shows the characteristics of privacy protection technology for different data types. Among text-based studies (n=366), 131 (35.8%) studies applied deidentification, 74 (20.2%) studies used anonymization, 15 (4.1%) studies combined both, 4 (1.1%) studies reported data hosting, 2 (0.5%) studies reported anonymization with data hosting, 6 (1.6%) studies used other methods, and 134 (36.6%) studies did not report. For image-based studies (n=56), 12 (21.4%) studies reported deidentification, 10 (17.9%) studies reported anonymization, 5 (8.9%) studies reported both, 1 (1.8%) study reported anonymization with data hosting, 1 (1.8%) study reported data hosting, and 27 (48.2%) studies did not report. For audio-based studies (n=2), one (50.0%) study reported anonymization and one (50.0%) study did not. For combined text and image studies (n=35), 14 (40.0%) studies used deidentification, 6 (17.1%) studies used anonymization, 3 (8.6%) studies used both, and 12 (34.3%) studies did not report. For text and audio studies (n=4), one (25.0%) study reported deidentification, and 3 (75.0%) studies did not. The single study using text, image, and audio data did not report its privacy protection method.

Table 3. Characteristics of privacy protection technology for different data types.

Type of data and privacy protection technology^a		Values, n (%)
Text (n=366)
	Deidentification	131 (35.8)
	Anonymization	74 (20.2)
	Deidentification + anonymization	15 (4.1)
	Data hosting	4 (1.1)
	Anonymization + data hosting	2 (0.5)
	Others^b	6 (1.6)
	Not reported	134 (36.6)
Images (n=56)
	Deidentification	12 (21.4)
	Anonymization	10 (17.9)
	Deidentification + anonymization	5 (8.9)
	Anonymization + data hosting	1 (1.8)
	Data hosting	1 (1.8)
	Not reported	27 (48.2)
Audio (n=2)
	Anonymization	1 (50.0)
	Not reported	1 (50.0)
Text+Images (n=35)
	Deidentification	14 (40.0)
	Anonymization	6 (17.1)
	Deidentification + anonymization	3 (8.6)
	Not reported	12 (34.3)
Text+Audio (n=4)
	Deidentification	1 (25.0)
	Not reported	3 (75.0)
Text + Images + Audio (n=1)
	Not reported	1 (100.0)

^aClassify according to the conditions reported in the original articles of the included studies.

^bAnonymization + data hosting + homomorphic encryption (n=1), anonymization + homomorphic encryption (n=1), federated learning (n=1), data augmentation (n=1), deidentification + data hosting (n=1), and homomorphic encryption (n=1).

Main Findings

In this scoping review, we identified 464 studies published between 2022 and 2025 that focus on the development and application of LLMs in health care using PHI. Strikingly, 256 (55.2%) of these studies were published in 2025 alone, compared with 188 (40.5%) studies in 2024, 19 (4.1%) studies in 2023, and only one (0.2%) study in 2022. This sharp increase highlights the extremely rapid pace of research in this emerging field and reflects the growing recognition of both the opportunities and challenges associated with LLM deployment in health care. These studies encompass a variety of countries, disease domains, and task types. Overall, the ethical reviews of these studies have been largely satisfactory. The vast majority of studies have reported on the approval of the ethics committee, ensuring that their procedures meet the relevant ethical standards. Nevertheless, there remains a shortfall in reporting on informed consent in certain prospective studies. It is concerning that a small number of LLM research projects using imaging data or retrospective data from electronic medical records fail to adequately report ethical review processes and the consideration of patient-informed consent, including whether consent was obtained or formally waived. Even when research involves only patient imaging data or retrospective data, it must still undergo rigorous ethical review [,]. Strict adherence to ethical review processes is essential to ensure the fairness and scientific integrity of medical research and to safeguard patient rights.

According to our findings, more than half of LLMs use cloud deployments, and the generative nature of LLMs can accidentally expose private data learned during training [], including PII []. And the vast parameter counts and extensive training corpora of LLMs enlarge their memorization footprint, leakage vectors, and prompt-manipulation surface, thereby exposing critical vulnerabilities that render these models prime targets for prompt-injection and data-poisoning attacks. Therefore, it is necessary to enhance the privacy protection of PHI. Cloud deployment offers the advantages of cost-effectiveness and scalability, as users are not required to invest in expensive hardware and can dynamically scale computing resources as needed. Additionally, cloud services provide established tools and global accessibility, facilitating rapid iteration and collaboration among distributed teams. However, cloud deployments also face significant data privacy risks, as data must be uploaded to third-party servers, which can lead to risks such as data breaches, unauthorized access, compliance issues, service disruptions, and model exploitation. These risks can be effectively mitigated through the integration of technical countermeasures like zero-trust architecture [], edge computing [], data encryption [], and access control.

Given the inherently high sensitivity of medical data and the significant risk of irreversible harm upon disclosure, the development of privacy-preserving safeguards for LLMs has become imperative. This requirement is not merely a technical prerequisite but also reflects an uncompromising mandate at the ethical and regulatory levels. In current research on the application of LLMs to health care, approximately one-third of the studies fail to mention any techniques for effectively protecting PHI. PHI includes PII such as patient names, addresses, Social Security numbers, and medical record numbers. Once compromised, such information can lead to serious privacy breaches and security risks. Therefore, removing PII is the first crucial step in safeguarding patient privacy [,]. By effectively eliminating or obfuscating these direct identifiers, it becomes possible to mitigate the risk of unauthorized access to PHI and thereby reduce the negative consequences of potential data breaches. The failure to prioritize PII protection in the deployment of LLMs within health care poses significant risks that extend beyond immediate privacy concerns. It threatens the integrity of patient-provider relationships, exposes individuals to financial and identity-related crimes, stifles technological and scientific progress, and raises critical ethical issues. Among the included studies, only one mentioned the use of federated learning techniques, and none used homomorphic encryption. Despite this, federated learning and homomorphic encryption are emerging as pivotal techniques for privacy-preserving in LLMs. Federated learning, due to its distributed training and decentralized model architecture, has gained significant traction in health care []. Future research should prioritize the development of comprehensive data privacy protection to facilitate the broader adoption of federated learning and homomorphic encryption in health care. Synthetic data generation has emerged as a promising solution to address privacy concerns in health care research and LLMs []. This approach uses AI models to create realistic, anonymized patient data that preserves privacy while enabling data access for secondary purposes []. While synthetic data offers benefits in promoting privacy, equity, safety, and continual learning, challenges remain, including the potential introduction of flaws and biases. Further research is needed to develop unified quality assessment metrics and address the current deficiency in longitudinal synthetic data generation [].

In studies involving PHI deidentification techniques or the use of anonymized data, the related descriptions are often very vague. Although these studies mention the removal of PII or the use of anonymized data, they typically do not specify which PII elements were removed or merely use ambiguous phrases such as “removing PII” or “using anonymized data,” lacking detailed technical explanations and transparency. First, the absence of clear technical descriptions undermines the credibility and reproducibility of the research, making it difficult for other researchers to replicate the results under the same conditions and thereby affecting the scientific validity and the effectiveness of subsequent applications. Second, privacy protection may be at risk because the lack of transparency in the deidentification process can result in PII not being fully removed, increasing the risk of data breaches. Finally, ethical issues arise as well. If the data processing for deidentification and anonymization is not sufficiently transparent, it can lead to ethical disputes regarding privacy protection and informed consent, especially when assessing whether there remains a risk of reidentifying individuals from the data. This lack of transparency may result in failing to meet the requirements of ethical reviews. According to the Food and Drug Administration, even deidentified data must retain traceability to meet regulatory requirements. Traceability after deidentification is not only a critical component of privacy protection but also essential for ensuring data availability, compliance, and credibility. It plays an indispensable role in data sharing, research transparency, emergency response, and other areas, providing a robust foundation for data-driven decision-making and innovation. When designing and implementing deidentification schemes, the need for traceability must be carefully considered to achieve a balance between privacy protection and data utility. In addition, the descriptions of “de-identification assessment” provided in current studies often lack transparency, leaving their scope and rigor unclear. For instance, it remains uncertain whether such assessments involved quantitative estimation of reidentification risk, reference to regulatory standards such as HIPAA Safe Harbor, or validation by external independent experts. The absence or ambiguity of these elements makes it difficult to determine the effectiveness and compliance of deidentification practices. Future studies should explicitly report these aspects in both methodology and results to ensure greater rigor and credibility in protecting patient privacy.

The HIPAA establishes standards and practices for deidentifying PHI. According to this rule, there are 2 methods for deidentifying PHI: expert determination, which requires a formal assessment by a qualified expert; and Safe Harbor, which involves the removal of specified identifiers so that covered entities and business associates cannot identify individuals from the remaining information. Although HIPAA does not explicitly use the term “anonymization,” anonymization is often considered an irreversible process that ensures data can no longer identify individuals. Anonymization requirements are more stringent than deidentification, as they guarantee that the data cannot be reidentified under any circumstances. While this study retains the original terminology used in the articles reviewed, most studies are vague in their descriptions of deidentification and anonymization, making it difficult to determine which specific methods were used. Researchers should clearly specify the approaches used to protect data privacy to ensure transparency and accuracy.

Medical big data exhibits unique multimodal characteristics. The term “multimodal” refers to the diverse sources and forms of medical data, which include laboratory data (eg, laboratory results), imaging data (eg, computed tomographic scans, x-rays, ultrasounds, and electrocardiograms), and video data containing audio (eg, fetal ultrasounds). Depending on the specific data type, its confidentiality, integrity, and availability are ensured through various methods. In our research, we found that current medical data privacy protection primarily relies on deidentification and anonymization techniques. However, in the context of multimodal medical data, a single privacy protection method is often insufficient to effectively prevent data leakage, tampering, and misuse. Therefore, designing multimodal data privacy protection technologies represents a critical direction for future research.

Strengths and Limitations

While existing literature reviews predominantly focus on the applications of LLMs in health care, there remains a notable gap in comprehensive scoping reviews that specifically evaluate privacy protection measures for PHI within LLM implementations (PHI-LLMs). Previous analyses addressing privacy concerns have primarily examined broader contexts rather than focusing specifically on patient information protection in language model applications, resulting in insufficient coverage of both technical safeguards and systemic compliance aspects within health care ecosystems.

A limitation of this study is that the evaluation of privacy protection measures relies solely on the information reported in published papers. Therefore, if certain studies have implemented privacy protection methods but did not disclose them in detail within their articles, we are unable to identify them. This situation may affect the comprehensiveness and accuracy of our evaluation. While we catalogued the adoption of different privacy protection methods, our review did not evaluate their security levels, implementation quality, or practical trade-offs. Future research should systematically assess the effectiveness and applicability of these techniques in health care-specific settings.

Implications for Research and Practice

Based on the 3 key findings outlined above, we offer the following additional recommendations for protecting patient privacy in health care–related LLM research, structured around 3 phases: study design, implementation, and reporting. When conducting research reports, the key terms can be referred to for a standardized design. The glossary of key terms () can be found in the .

Textbox 2. Glossary of key terms.

Protected health information: Individually identifiable health information relating to health status, care, or payment that is protected under the Health Insurance Portability and Accountability Act.
Personally identifiable information: It refers to any information that can directly or indirectly identify a specific individual, including name, ID number, address, contact information, and data that can identify identity when combined with other information. Personally identifiable information is a broad concept that encompasses all data that can identify an individual.
Deidentification (Safe Harbor, Health Insurance Portability and Accountability Act): Removal of 18 specified identifiers (eg, name, address, phone number, and dates) such that the data is no longer considered protected health information.
Deidentification (Ontario Guidance): A risk-based statistical approach that quantifies reidentification risk and determines whether it is acceptably small.
Anonymization (General Data Protection Regulation): Data is processed in such a way that reidentification is no longer possible by any means “reasonably likely to be used.”
Rule-based matching: Algorithmic detection and removal of direct identifiers (eg, names, addresses) using predefined rules or dictionaries.
Federated learning: A decentralized machine learning paradigm where models are trained collaboratively without exchanging raw data.
Reidentification protection technology: Technical and organizational measures (eg, k-anonymity and differential privacy) that reduce the likelihood of reidentifying individuals, acknowledging that zero risk is unattainable but very low residual risk is acceptable under most regulations.
Direct identifiers: Variables that can uniquely and directly identify an individual, such as name, social security number, phone number, full address, and medical record number.
Indirect identifiers (quasi-identifiers): Variables that cannot identify an individual alone but may enable reidentification when combined with other data, such as age, gender, zip code, and admission date.

Considerations in Research Design

In the design phase of LLM research, patient privacy protection must be prioritized. First, the data minimization principle should be strictly adhered to, meaning only the minimum necessary PHI required to achieve the research objectives should be collected and used []. Second, a clear definition of research purpose and usage scope is essential, ensuring that all PII used has a well-defined purpose and is not repurposed for unauthorized studies or commercial applications. Additionally, ethical approval and informed consent are critical components of the design phase. Researchers must submit detailed research plans to an Institutional Review Board or Ethics Committee, outlining how PII will be obtained, used, and protected. Where applicable, obtaining informed consent from patients is necessary to ensure they are aware of how their data will be used and safeguarded.

Considerations in Research Implementation

In the implementation phase, priority should be given to deploying the LLM locally. During model training, multiple patient privacy protection strategies such as deidentification, anonymization, federated learning, synthetic data, and differential privacy should be used. Due to the potential risk of reidentification, continuous security monitoring and auditing are indispensable. The research team should conduct regular security assessments and vulnerability scans to promptly identify and address potential security vulnerabilities. Postbreach responses also constitute an indispensable part of a comprehensive privacy protection framework. Effective incident response should include rapid detection, containment, patient notification, and remediation strategies, which are increasingly emphasized in health care data governance guidelines.

Considerations in Research Reporting

Research reports should fully embody the principles of transparency and reproducibility. Researchers should disclose in detail the data sources, ethical approval processes, informed consent procedures, and privacy protection techniques used. Selecting appropriate reporting guidelines (such as STROBE [], STARD [], CONSORT-AI [Consolidated Standards of Reporting Trials–Artificial Intelligence] [], and TRIPOD-LLM []) can improve report quality and provide a reference for other researchers.

Conclusions

Our scoping review sounds an alarm on the inadequately addressed imperative of patient privacy protection in medical research using LLMs. In response, we formulate comprehensive recommendations for the study design, implementation, and reporting phases to fortify PHI protection and foster transparency in PHI-LLM research. Our findings compellingly argue for the urgent development of stricter regulatory frameworks and the integration of advanced privacy-preserving technologies to safeguard PHI. It is anticipated that such measures will enable future health care applications of LLMs to achieve a balance between innovation and rigorous patient privacy protection, thus elevating ethical standards and scientific credibility.

The data generated during the scoping review are available from the corresponding author on reasonable request. However, the majority of such data have been presented on paper in tables, figures, and text.

This study is supported by the National Key Research and Development Program of China (numbers 2022YFC3502300 and 2022YFC3502305). The funders had no role in considering the study design or in the collection, analysis, interpretation of data, writing of the report, or decision to submit the article for publication.

ZXY and LSY conceptualized the study, defined the methodology, performed the database searches, and managed the screening process. ZXY and LSY also performed data extraction and authored the original draft. CZ, YDD, and WSJ reviewed the literature, charted the data, and conducted the analyses. GL, YLZ, and SHC provided supervision and contributed to the writing review. All authors contributed to the discussion of literature screening, data extraction, and writing of the paper. All authors reviewed and approved the final version of the paper. The corresponding author attests that all listed authors meet authorship criteria and that no others meeting the criteria have been omitted. All authors affirm that the manuscript is an honest, accurate, and transparent account of the study being reported; that no important aspects of the study have been omitted; and that any discrepancies from the study as planned (and, if relevant, registered) have been explained.

None declared.

Edited by A Coristine; submitted 26.Apr.2025; peer-reviewed by P Han, Z Hou, L Pilgram; comments to author 16.Jul.2025; revised version received 02.Nov.2025; accepted 03.Nov.2025; published 21.Nov.2025.

©Xiaoying Zhong, Siyi Li, Zhao Chen, Long Ge, Dongdong Yu, Shijia Wang, Liangzhen You, Hongcai Shang. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 21.Nov.2025.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research (ISSN 1438-8871), is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.

Continue Reading

November 21, 2025

Bitcoin and other crypto assets sink in flight from risk

Bitcoin and ether slumped to multi-month lows on Friday, with cryptocurrencies swept up in a broader flight from riskier assets as investors worried about lofty tech valuations and bets on near-term U.S. interest rate cuts faded.

Bitcoin, the world’s largest cryptocurrency, fell 5.5% to a seven-month low of $81,668. Ether slid more than 6% to $2,661.37, its lowest in four months.

Both tokens are down roughly 12% so far this week.

Cryptocurrencies are often viewed as a barometer of risk appetite and their slide highlights how fragile the mood in markets has turned in recent days, with high-flying artificial intelligence stocks tumbling and volatility spiking VIX.

“If it’s telling a story about risk sentiment as a whole, then things could start to get really, really ugly, and that’s the concern now,” Tony Sycamore, a market analyst at IG, said of the fall in bitcoin.

About $1.2 trillion has been wiped off the market value of all cryptocurrencies in the past six weeks, according to market tracker CoinGecko.

Bitcoin’s slide follows a stellar run this year that propelled it to a record high above $120,000 in October, buoyed by favourable regulatory changes towards crypto assets globally.

But analysts say the market remains scarred by a record single-day slump last month that saw more than $19 billion of positions liquidated.

“The market feels a little bit dislocated, a bit fractured, a bit broken, really, since we had that selloff,” said Sycamore.

Bitcoin has since erased all its year-to-date gains and is now down 12% for the year, while ether has lost close to 19%.

Citi analyst Alex Saunders said $80,000 would be an important level as it is around the average level of bitcoin holdings in ETFs.

The selloff has also hurt share prices of crypto stockpilers, following a boom in public digital asset treasury companies this year as corporates took advantage of rising prices to buy and hold cryptocurrencies on their balance sheets.

Shares of Strategy, once the poster child for corporate bitcoin accumulation, have fallen 11% this week and were down nearly 4% in premarket trade, languishing at one-year lows.

JP Morgan said in a note this week that the company could be excluded from some MSCI equity indexes, which could spark forced selling by funds that track them.

Its Japanese peer Metaplanet has tumbled about 80% from a June peak.

Crypto exchange Coinbase was down 1.9% in premarket trade and is on course for its longest losing streak in more than a month.

Crypto miners MARA Holdings and CleanSpark were down 2.4% and 3.6%, respectively, while the Winklevoss twins’ newly-listed Gemini has plunged 62% from its listing price.

“Bitcoin market conditions are the most bearish they have been since the current bull cycle started in January 2023,” said digital asset research firm CryptoQuant in its weekly crypto report on Wednesday.

“We are highly likely to have seen most of this cycle’s demand wave pass.”

Continue Reading

November 21, 2025
Europe’s economy is geared towards a disappearing world, says ECB’s Lagarde | European Central Bank

Europe’s economy is “geared towards a world that is gradually disappearing”, according to a warning from Christine Lagarde that the EU needs reforms to spur growth.

The president of the European Central Bank (ECB) said the EU’s dependence on international trade had left it vulnerable, as major partners had turned away from the trade that made the bloc’s exporters wealthy.

Donald Trump has led a global turn towards protectionism and against globalisation, with steep tariffs imposed on almost every trading partner. At the same time, China has used its dominance of production of certain critical materials and products to exert pressure.

Lagarde argued that Europe was vulnerable because of a “dependency on third countries for our security and the supply of critical raw materials”. She cited China’s control of the supply of rare earth metals that are crucial in electric motors and wind turbines, as well as the “choke point” of power chips made by Nexperia in China that threatened to shut down production across the global car industry.

Speaking at the European Banking Congress in Frankfurt, Germany, Lagarde said Europe had failed to address its own problems. Policymakers had instead allowed its weaknesses to “erode growth quietly, as each new shock nudges us onto a slightly lower trajectory”.

“Our internal market has stood still, especially in the areas that will shape future growth, like digital technology and artificial intelligence, as well as the areas that will finance it, such as capital markets,” she said.

Europe also faced a “vicious circle” of its own savers allocating money to US stocks, helping the American economy to advance faster than the EU and leaving “stagnating productivity at home and growing dependence on others”, she said.

Lagarde did highlight some European strengths as well, including a resilient labour market, increasing digital investment, and government spending, particularly on defence in response to Russia’s invasion of Ukraine, that has counteracted economic slowdown.

Part of Lagarde’s prescription for recovery was lowering barriers to services and goods trade between EU countries. Those barriers are equivalent to a 100% tariff on services and 65% on goods, according to ECB analysis. Lowering those barriers to the same level as the Netherlands – a relatively open economy – would fully make up for the hit from US tariffs, she said.

skip past newsletter promotion

Sign up to Business Today

Get set for the working day – we’ll point you to all the business news and analysis you need every morning

Privacy Notice: Newsletters may contain information about charities, online ads, and content funded by outside parties. If you do not have an account, we will create a guest account for you on theguardian.com to send you this newsletter. You can complete full registration at any time. For more information about how we use your data see our Privacy Policy. We use Google reCaptcha to protect our website and the Google Privacy Policy and Terms of Service apply.

after newsletter promotion

She called for mutual recognition of regulated companies, allowing them to sell across Europe when authorised by any one country. She also said the EU should adopt qualified majority voting on tax, preventing any single member state from vetoing changes.

She argued that benefits would include allowing the harmonisation of VAT, making it easier for smaller European companies to gain access to the whole EU market without having to comply with 27 different tax regimes.

Continue Reading

November 21, 2025
Citius Oncology to Advance Commercial Launch of LYMPHIR™ with Verix AI Integration

Leading edge artificial intelligence and machine learning platform supports enhanced salesforce targeting and engagement for cutaneous T-cell lymphoma immunotherapy launch

CRANFORD, N.J., Nov. 21, 2025 /PRNewswire/ — Citius Oncology, Inc. (“Citius Oncology”) (Nasdaq: CTOR), the oncology-focused subsidiary of Citius Pharmaceuticals, Inc. (“Citius Pharma”) (Nasdaq: CTXR), a late-stage biopharmaceutical company developing and commercializing first-in-class critical care products, today announced a deeper collaboration with Verix, a leader in AI-powered commercial optimization technology for the life sciences sector. Citius Oncology’s commercial team intends to further leverage Verix’s innovative Tovana platform to support the anticipated fourth quarter 2025 U.S. commercialization of LYMPHIR™ (denileukin diftitox-cxdl), a novel immunotherapy approved by the U.S. Food and Drug Administration (FDA) for the treatment of adult patients with relapsed or refractory Stage I-III cutaneous T-cell lymphoma (CTCL) after at least one prior systemic therapy.

Verix’s Tovana platform integrates advanced analytics, real-world claims data, and machine learning to help inform Citius Oncology’s commercial strategy and enable real-time field execution. The platform refines targeting over time and supports data-driven decisions, allowing the Citius Oncology commercial team to embed predictive intelligence into sales and marketing plans, and to prioritize engagement with high-impact healthcare providers (HCPs). Using company-defined criteria, the system identifies patterns in treatment and diagnosis, enabling Citius Oncology’s commercial team to promptly engage prescribers whose patients may benefit from LYMPHIR.

“We are committed to leveraging leading-edge technologies to maximize the commercial impact of LYMPHIR and look forward to using this innovative AI platform to amplify the precision and impact of our experienced commercial and marketing teams,” stated Leonard Mazur, Chairman and CEO of Citius Oncology and Citius Pharma. “Through our collaboration with Verix, we are able to enhance our salesforce’s experience with the ability to identify key treatment patterns, personalize provider engagement, and allocate commercial resources efficiently. With LYMPHIR poised to become a meaningful new option for patients with relapsed or refractory CTCL, it’s critical that our commercial organization has precision tools that accelerate physician engagement and product uptake. This data-driven approach positions us to execute a focused and impactful launch while maintaining a lean infrastructure,” added Mazur.

“We are proud to partner with Citius Oncology at this critical stage in their commercialization journey,” said Doron Aspitz, CEO of Verix. “The Tovana platform is designed to empower life sciences commercial organizations to move from retrospective analysis to real-time action. With Citius Oncology, we see a strong alignment in using AI to bridge data with execution, and we are excited to help deliver meaningful insights that can accelerate the reach of an innovative therapy like LYMPHIR.”

This initiative builds upon foundational launch activities including the establishment of distribution partnerships, permanent reimbursement codes (J-code: J9161), and inclusion in the National Comprehensive Cancer Network (NCCN) Guidelines. Commercial availability of LYMPHIR in the U.S. is expected in the fourth quarter of 2025.

Citius Oncology believes that integrating Verix’s AI capabilities will not only enable faster market penetration but also deliver durable advantages as the company builds its oncology franchise. This initiative reflects Citius Oncology’s disciplined focus on capital efficiency, executional excellence, and sustainable value creation for shareholders. Most importantly, it reflects the company’s commitment to facilitating access to care for patients living with cutaneous T-cell lymphoma.

About LYMPHIR™ (denileukin diftitox-cxdl)

LYMPHIR is a targeted immune therapy for relapsed or refractory cutaneous T-cell lymphoma (CTCL) indicated for use in Stage I-III disease after at least one prior systemic therapy. It is a recombinant fusion protein that combines the IL-2 receptor binding domain with diphtheria toxin (DT) fragments. The agent specifically binds to IL-2 receptors on the cell surface, causing diphtheria toxin fragments that have entered cells to inhibit protein synthesis. After uptake into the cell, the DT fragment is cleaved and the free DT fragments inhibit protein synthesis, resulting in cell death. Denileukin diftitox-cxdl demonstrated the ability to deplete immunosuppressive regulatory T lymphocytes (Tregs) and antitumor activity through a direct cytocidal action on IL-2R-expressing tumors.

In 2021, denileukin diftitox received regulatory approval in Japan for the treatment of relapsed or refractory CTCL and peripheral T-cell lymphoma (PTCL). Subsequently, in 2021, Citius acquired an exclusive license with rights to develop and commercialize denileukin diftitox in all markets except for India, Japan and certain parts of Asia. LYMPHIR (denileukin diftitox-cxdl) was approved by the FDA in August 2024.

About Cutaneous T-cell Lymphoma

Cutaneous T-cell lymphoma is a type of cutaneous non-Hodgkin lymphoma (NHL) that comes in a variety of forms and is the most common type of cutaneous lymphoma. In CTCL, T-cells, a type of lymphocyte that plays a role in the immune system, become cancerous and develop into skin lesions, leading to a decrease in the quality of life of patients with this disease due to severe pain and pruritus. Mycosis Fungoides (MF) and Sézary Syndrome (SS) comprise the majority of CTCL cases. Depending on the type of CTCL, the disease may progress slowly and can take anywhere from several years to upwards of ten to potentially reach tumor stage. However, once the disease reaches this stage, the cancer is highly malignant and can spread to the lymph nodes and internal organs, resulting in a poor prognosis. Given the duration of the disease, patients typically cycle through multiple agents to control disease progression. CTCL affects men twice as often as women and is typically first diagnosed in patients between the ages of 50 and 60 years of age. Other than allogeneic stem cell transplantation, for which only a small fraction of patients qualify, there is currently no curative therapy for advanced CTCL.

INDICATION

LYMPHIR is an IL2-receptor-directed cytotoxin indicated for the treatment of adult patients with r/r Stage I-III cutaneous T-cell lymphoma (CTCL) after at least one prior systemic therapy.

IMPORTANT SAFETY INFORMATION

BOXED WARNING: CAPILLARY LEAK SYNDROME

Capillary leak syndrome (CLS), including life-threatening or fatal reactions, can occur in patients receiving LYMPHIR. Monitor patients for signs and symptoms of CLS during treatment. Withhold LYMPHIR until CLS resolves, or permanently discontinue based on severity.

WARNINGS AND PRECAUTIONS

Capillary Leak Syndrome

LYMPHIR can cause capillary leak syndrome (CLS), including life-threatening or fatal reactions. CLS was defined in the clinical trials as the occurrence of at least 2 of the following symptoms at any time during LYMPHIR therapy: hypotension, edema, and serum albumin <3 g/dL. These symptoms were not required to occur simultaneously to be characterized as capillary leak syndrome.

As defined, CLS occurred in 27% of patients in the pooled population across 3 clinical trials, including 8% with Grade 3. There was one (0.8%) fatal occurrence of CLS. Of the patients with CLS, 22% had recurrence. The majority of CLS events (81%) occurred within the first 2 cycles of treatment. The median time to onset from Cycle 1, Day 1 was 6.5 days (range: 1 to 77), the median duration of CLS was 14 days (range: 2 to 40), and 75% of patients had resolution. The most common symptoms included edema, hypoalbuminemia, and hypotension. Pleural effusion, pericardial effusion, and dehydration also occurred.

Regularly assess patients for weight gain, new onset or worsening of edema, dyspnea, and hypotension (including orthostatic changes). Monitor serum albumin levels prior to the initiation of each cycle of therapy and more often as clinically indicated.

Withhold, reduce dose, or permanently discontinue based on severity. If LYMPHIR is withheld, resume LYMPHIR following resolution of CLS and when serum albumin is greater than or equal to 3 g/dL.

Visual Impairment

LYMPHIR can cause serious visual impairment, including changes in visual acuity and color vision. In the pooled population across 3 clinical trials, visual impairment occurred in 9%, with Grade 1 in 8% and Grade 2 in 1%. The most commonly reported symptom was blurred vision. Of the patients with visual impairment, 67% had resolution of their visual impairment.

Perform baseline ophthalmic examination and monitor as clinically indicated. If patients experience symptoms of visual impairment, such as changes in visual acuity, changes in color vision, or blurred vision, refer for ophthalmologic evaluation.

Withhold LYMPHIR until visual impairment resolves or permanently discontinue based on severity.

Infusion-Related Reactions

LYMPHIR can cause serious infusion-related reactions. Infusion-related reactions were reported in 69% of patients in the pooled population across 3 clinical trials of patients who received LYMPHIR, with Grade 3 infusion-related reactions in 3.4%. Eighty-three percent of infusion-related reactions occurred in Cycles 1 and 2. The most common symptoms included nausea, fatigue, chills, musculoskeletal pain, vomiting, fever, and arthralgia.

Premedicate patients for the first three cycles prior to starting a LYMPHIR infusion. Monitor patients frequently during infusion. For Grade 2 or higher infusion reactions, premedicate at least 30 minutes prior to each subsequent infusion with a systemic steroid for at least 3 cycles.

Interrupt or discontinue LYMPHIR based on severity. Institute appropriate medical management.

Hepatotoxicity

LYMPHIR can cause hepatotoxicity. In the pooled safety population, elevated ALT occurred in 70% of patients, with Grade 3 ALT occurring in 22%; elevated AST occurred in 64% of patients, with Grade 3 AST elevation occurring in 9%. For Grade 3 events, median time to onset was 8 days (range: 1 to 15 days); median time to resolution was 15 days (range: 7 to 50 days); all cases of Grade 3 ALT or AST elevations resolved. Elevated total bilirubin occurred in 5% of patients, with Grade 3 occurring in 0.9%.

Monitor liver enzymes and bilirubin at baseline and during treatment as clinically indicated. Withhold, reduce dose, or permanently discontinue LYMPHIR based on severity.

Embryo-Fetal Toxicity

Based on its mechanism of action, LYMPHIR can cause fetal harm when administered to a pregnant woman. Verify the pregnancy status of females of reproductive potential prior to the initiation of LYMPHIR. Advise pregnant women of the potential risk to the fetus. Advise females of reproductive potential to use effective contraception during treatment and for 7 days following the last dose of LYMPHIR.

ADVERSE REACTIONS

The most common adverse reactions (≥20%), including laboratory abnormalities, are increased transaminases, albumin decreased, nausea, edema, hemoglobin decreased, fatigue, musculoskeletal pain, rash, chills, constipation, pyrexia, and capillary leak syndrome.

USE IN SPECIFIC POPULATIONS

Pregnancy

Risk Summary
Based on its mechanism of action, LYMPHIR can cause fetal harm when administered to a pregnant woman. There are no available data on the use of LYMPHIR in pregnant women to evaluate for a drug-associated risk. No animal reproductive and developmental toxicity studies have been conducted with denileukin diftitox.

Denileukin diftitox-cxdl causes depletion of regulatory T lymphocytes (Treg), immune activation, and capillary leak syndrome, compromising pregnancy maintenance. Advise pregnant women of the potential risk to a fetus.

In the U.S. general population, the estimated background risk of major birth defects and miscarriage in clinically recognized pregnancies are 2-4% and 15-20%, respectively.

Lactation

Risk Summary
No data are available regarding the presence of denileukin diftitox-cxdl in human milk, the effects on the breastfed child, or on milk production. Because of the potential for serious adverse reactions in breastfed children, advise women not to breastfeed during treatment with LYMPHIR and for 7 days after the last dose.

Females and Males of Reproductive Potential

Based on its mechanism of action, LYMPHIR can cause fetal harm when administered to a pregnant woman.

Pregnancy Testing
Verify the pregnancy status of females of reproductive potential prior to initiating LYMPHIR.

Contraception

Females
Advise females of reproductive potential to use effective contraception during treatment with LYMPHIR and for 7 days after the last dose.

Infertility

Males
Based on findings in rats, male fertility may be compromised by treatment with LYMPHIR. The reversibility of the effect on fertility is unknown.

Pediatric Use
Safety and effectiveness of LYMPHIR in pediatric patients have not been established.

Geriatric Use
Of the 69 patients with Stage I-III r/r CTCL who received LYMPHIR, 34 patients (49%) were 65 years of age and older and 10 patients (14%) were 75 years of age and older. Clinical studies of LYMPHIR did not include sufficient numbers of patients 65 years of age and older to determine whether they respond differently from younger adult patients.

You may report side effects to the FDA at 1-800-FDA-1088 or www.fda.gov/medwatch. You may also report side effects to Citius Oncology at 1-844-459-6744.

Please read Important Safety Information and full Prescribing Information, including Boxed WARNING, for LYMPHIR.

About Verix

Verix is a leading provider of advanced commercial optimization solutions for the life sciences industry. Its flagship product, Tovana™, is a patented, AI-powered SaaS platform that enables life science companies to optimize commercial strategy and execution. Tovana integrates cutting-edge technology, advanced machine learning and deep domain expertise into a single, intuitive platform, to transform how life science companies deploy data-driven strategies. The platform analyzes large volumes of data, enabling companies to continuously and consistently automate key commercial functions such as healthcare provider (HCP) targeting, precision forecasting, omnichannel engagement, and patient identification.

Trusted by Fortune 500 pharmaceutical companies around the world, Verix’s innovative Tovana platform helps teams turn complex data into clear, actionable insights that drive brand performance. Tovana’s agile and easy-to-use platform accelerates decision-making, improves launch execution, and enhances commercial outcomes. For more information, visit www.verix.com.

About Citius Oncology, Inc.

Citius Oncology, Inc. (Nasdaq: CTOR) is a platform to develop and commercialize novel targeted oncology therapies. In August 2024, its primary asset, LYMPHIR, was approved by the FDA for the treatment of adults with relapsed or refractory Stage I–III CTCL who had had at least one prior systemic therapy. Management estimates the initial market for LYMPHIR currently exceeds $400 million, is growing, and is underserved by existing therapies. Robust intellectual property protections that span orphan drug designation, complex technology, trade secrets and pending patents for immuno-oncology use as a combination therapy with checkpoint inhibitors would further support Citius Oncology’s competitive positioning. For more information, please visit www.citiusonc.com.

About Citius Pharmaceuticals, Inc.

Citius Pharmaceuticals, Inc. (Nasdaq: CTXR) is a biopharmaceutical company dedicated to the development and commercialization of first-in-class critical care products. In August 2024, the FDA approved LYMPHIR, a targeted immunotherapy for an initial indication in the treatment of adults with relapsed or refractory Stage I–III CTCL who had had at least one prior systemic therapy. Citius Pharma’s late-stage pipeline also includes Mino-Lok^®, a catheter lock solution to salvage catheters in patients with catheter-related bloodstream infections, and CITI-002 (Halo-Lido), a topical formulation for the relief of hemorrhoids. A pivotal Phase 3 trial for Mino-Lok and a Phase 2b trial for Halo-Lido were completed in 2023. Mino-Lok met primary and secondary endpoints of its Phase 3 trial. Citius is actively engaged with the FDA to outline next steps for both programs. Citius Pharmaceuticals owns 79% of Citius Oncology. For more information, please visit www.citiuspharma.com.

Forward-Looking Statements

This press release may contain “forward-looking statements” within the meaning of Section 27A of the Securities Act of 1933 and Section 21E of the Securities Exchange Act of 1934. Such statements are made based on our expectations and beliefs concerning future events impacting Citius Pharma or Citius Oncology. You can identify these statements by the fact that they use words such as “will,” “anticipate,” “estimate,” “expect,” “plan,” “should,” and “may” and other words and terms of similar meaning or use of future dates. Forward-looking statements are based on management’s current expectations and are subject to risks and uncertainties that could negatively affect our business, operating results, financial condition and stock price. Factors that could cause actual results to differ materially from those currently anticipated, and, unless noted otherwise, that apply to Citius Pharma and Citius Oncology, are: our need for substantial additional funds and our ability to raise additional money to fund our operations for at least the next 12 months as a going concern; our ability to commercialize LYMPHIR and any of our other product candidates that may be approved by the FDA; our ability to use the latest technology to support our commercialization efforts; our ability to maintain Nasdaq’s continued listing standards; our ability to successfully implement and maintain distribution agreements with current or other future distribution partners; potential disruptions or performance issues involving third-party logistics providers; the estimated markets for our product candidates and the acceptance thereof by any market; the ability of our product candidates to impact the quality of life of our target patient populations; risks relating to the results of research and development activities, including those from our existing and any new pipeline assets; our dependence on third-party suppliers; our ability to procure cGMP commercial-scale supply; our ability to obtain, perform under and maintain financing and strategic agreements and relationships; uncertainties relating to preclinical and clinical testing; the early stage of products under development; market and other conditions; risks related to our growth strategy; patent and intellectual property matters; our ability to identify, acquire, close and integrate product candidates and companies successfully and on a timely basis; government regulation; competition; as well as other risks described in our Securities and Exchange Commission (“SEC”) filings. These risks have been and may be further impacted by any future public health risks. Accordingly, these forward-looking statements do not constitute guarantees of future performance, and you are cautioned not to place undue reliance on these forward-looking statements. Risks regarding our business are described in detail in our SEC filings which are available on the SEC’s website at www.sec.gov, including in Citius Oncology’s and Citius Pharma’s Annual Reports on Forms 10-K for the year ended September 30, 2024, filed with the SEC on December 27, 2024, each as amended on January 27, 2025, as updated by our subsequent filings with the SEC. These forward-looking statements speak only as of the date hereof, and we expressly disclaim any obligation or undertaking to release publicly any updates or revisions to any forward-looking statements contained herein to reflect any change in our expectations or any changes in events, conditions or circumstances on which any such statement is based, except as required by law.

Investor Contact:

Ilanit Allen
[email protected]
908-967-6677 x113

Media Contact:

STiR-communications
Greg Salsburg
[email protected]

SOURCE Citius Oncology, Inc.

Continue Reading

November 21, 2025
Accelerating progress in immune cell therapy for solid tumours
Parums, D. V. A review of CAR T cells and adoptive T-cell therapies in lymphoid and solid organ malignancies. Med. Sci. Monit. 31, e948125 (2025).

PubMed

Google Scholar
Uslu, U. & June, C. H. Beyond the blood: expanding CAR T cell therapy to solid tumors. Nat. Biotechnol. 43, 506–515 (2025).

Article
PubMed

Google Scholar
Salas-Benito, D., Berger, T. R. & Maus, M. V. Stalled CARs: Mechanisms of resistance to CAR T cell therapies. Annu. Rev. Cancer Biol. 7, 23–42 (2023).

Article

Google Scholar
Galassi, C., Chan, T. A., Vitale, I., & Galluzzi, L. The hallmarks of cancer immune evasion. Cancer Cell, 42, 1825–1863 (2024).

Article
PubMed

Google Scholar
Li, Y-R., Zhu, Y., Halladay, T. & Yang, L. In vivo CAR engineering for immunotherapy. Nat. Rev. Immunol. 25, 725–744 (2025).

Article
PubMed

Google Scholar

Continue Reading

By 2031, health care expenditures in the United States are expected to approach 20% of the gross domestic product, surpassing other high-income nations with comparable clinical resources []. A significant driver of these costs is the fee-for-service payment model, which incentivizes the use of costly health care resources and services, even though they may not improve patient outcomes or quality of life. The Medicare Access and Children’s Health Insurance Program Reauthorization Act of 2015 marked a pivotal transition from a volume-oriented to value-based payment model for health care services [-]. Concurrently, the Centers for Medicare and Medicaid Services have prioritized development of patient-centered measures, incorporating patient-reported outcomes (PROs), such as the Patient-Reported Outcomes Measurement Information System (PROMIS), into quality evaluation and pay-for-performance programs [].

These changes are important because patients and clinicians increasingly grapple with rising health care costs while striving to maintain high-quality care. The burden of health care expenses disproportionately affects patients with chronic, complex diseases such as advanced cancer and chronic kidney disease (CKD) [-]. These patients often experience distressing symptoms like fatigue, pain, anxiety, and depression [-]. These symptoms frequently go unnoticed during routine visits, leading to unmanaged symptoms and a greater likelihood of potentially avoidable health care resource use [-]. Financial strain has also been linked to increased patient debt and bankruptcy [-].

Given this financial strain, patients may be more willing to engage in shared decision-making (SDM) with clinicians, collaboratively weighing the benefits and risks of treatment options to align health care decisions with their preferences and values [-]. The growing engagement with digital health care presents an opportunity for innovative health IT solutions, such as PRO-based clinical dashboards that provide decision-making information in a format that benefits both patients and clinicians. These dashboards track clinical and health outcome trends over time, potentially reducing the risk of unplanned or low-benefit health services use by enabling early intervention in symptom management and fostering SDM discussions about bothersome side effects and treatment alternatives [,,]. Prior studies have suggested that early symptom management may reduce acute care use and improve quality of life [,,]. We hypothesized that PRO-based clinical dashboards could empower patients with complex diseases to visualize the relationship between interventions and outcomes, thereby reducing unnecessary spending while delivering high-value care more effectively [].

Although PROs and SDM have been shown to be effective in symptom monitoring for patients with cancer and CKD, their influence on reducing the use of potentially unnecessary health services of limited benefit is less understood [,,,,]. Our previous work showed that a PRO-based dashboard enhanced SDM and reduced patient anxiety [], yet the specific role of SDM in reducing health care use remains unclear. While some studies suggest that SDM tools may reduce health care use, a Cochrane review [,] found mixed results, with inconsistent effects on use, outcomes, and costs, and no consistent reduction in invasive or expensive treatments [].

In this study, we focus on the potential for PRO-based dashboards to influence the use of potentially unnecessary, expensive, and low-benefit health care services, improving SDM, enhancing symptom management, and engaging patients in care optimization. We hypothesize that patients using the dashboard will show reduced use of these services compared to a matched cohort not exposed to the dashboard [].

Dashboard Design, Content, and Integration With Clinical Workflow

The development and integration of the dashboard, including its co-design process, visual elements, included assessments, and the ways physicians used it, have been comprehensively described elsewhere [,]. Briefly, the dashboard was co-designed with the collective effort of 20 diverse stakeholders, including patients, clinicians, care partners, investigators, and health IT professionals. The goal was to support symptom management and facilitate SDM during health care visits for patients with advanced cancer or CKD. Integrated into Northwestern Medicine’s electronic health record system, the dashboard displays PROs along with other clinical data. Clinicians were encouraged to use the dashboard, updated in real time, during clinical encounters with patients who met the study’s inclusion criteria.

Three days before a scheduled visit, patients were prompted to complete a PRO questionnaire (), which assessed symptoms and supportive care needs. The questionnaire included PROMIS measures to assess anxiety, depression, pain, fatigue, and physical functioning. In addition, patients responded to five open-ended questions in the “symptoms and goals” section, which populated the dashboard. These questions focused on (1) top concerns for discussion, (2) the most troubling side effects, (3) overall goals for their cancer or CKD treatment, (4) personal goals and values, and (5) potential ways to collaborate with their care team to achieve these goals. Patient responses were automatically scored, recorded in the electronic health record, and generated alerts to their care team if any clinically significant symptoms or needs were identified. Clinicians then used this information, along with the patient’s clinical data from the dashboard, to facilitate SDM and improve communication between patients and care teams.

Study Design and Location

We conducted a propensity score–weighted, difference-in-differences (DiD) analysis [] to determine the association between dashboard use and high-cost health services use. The study protocol has previously been published []. This manuscript adheres to the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines for cohort studies.

Ethical Considerations

All study activities were reviewed and approved by the Northwestern University Institutional Review Board (protocols STU00210091, STU00211654, and STU00212634). Health services use data were extracted from the Northwestern Medicine Enterprise Data Warehouse by trained Northwestern Medicine data analysts and entered into the study’s REDCap database by the study coordinator (AC), as approved by the ethics committee. All study procedures were considered low risk by the Northwestern University Institutional Review Board, and the ethics review concluded that the benefits outweighed any minimal risks. Participants provided informed consent to complete a follow-up survey at 3 and 6 months. Participants did not receive any incentives for enrollment or survey completion.

All data were aggregated by an Enterprise Data Warehouse (EDW) analyst prior to analysis, and no protected health information (PHI) was visible to the research team. Limited variables—such as medical record number (MRN), race/ethnicity, and age—were retained solely to enable patient-level linkage and inclusion as covariates in multivariable analyses. All data were stored on secure, access-controlled institutional servers, and no identifiers were shared outside the research environment. All study procedures adhered to institutional privacy and confidentiality standards and complied with the Health Insurance Portability and Accountability Act (HIPAA) regulations.

Participants and Eligibility Criteria

The intervention group consisted of Northwestern Medicine patients in Chicago, Illinois, diagnosed with advanced cancer or CKD between June 2020 and January 2022 who had previously received care from at least one clinician participating in the study (). These clinicians at Northwestern Memorial Health Care included 2 oncologists, a nephrologist, a nephrology physician assistant, and 2 primary care physicians. Patients also consented to follow-up surveys at 3- and 6-month intervals. Patients with advanced cancer were defined as having either stage IV gastrointestinal cancer receiving intravenous chemotherapy for at least 3 months or stage III or IV lung cancer undergoing first- or second-line chemotherapy for at least 3 months. Patients with CKD required a confirmed diagnosis of at least stage III CKD or an estimated glomerular filtration rate (eGFR) below 60. For the intervention group, the baseline date was defined individually as the date on which each participant completed the initial dashboard questionnaire from June 8, 2020, to November 1, 2022. For the comparison group, we identified patients with advanced cancer and CKD not exposed to the dashboard. The inclusion criteria were patients who received care from Northwestern Medicine clinicians who participated in the dashboard study but chose not to enroll in it or patients who received care during the same time period from Northwestern Medicine clinicians who were not involved in the dashboard study.

For patients with advanced cancer in the comparison group, the baseline date was determined as the visit closest to the intervention patient’s baseline date (within 30 days) during the established time frame for the dashboard baseline (June 8, 2020, to November 1, 2022). For CKD comparison patients, the baseline was similarly defined as the first instance where their eGFR dropped below 60, adjusted to align with the intervention patients’ baseline date within the same time frame. To account for variability in eGFR, the mean baseline eGFR for each patient was calculated using eGFR values within 30 days of the baseline date for both groups. Patients with a mean eGFR above 60, indicating CKD stage II or lower, were excluded to ensure comparability in disease severity. Because this was a pragmatic, real-world evaluation, no power calculation was performed a priori. Instead, we included every patient who met the above eligibility criteria during the June 2020 to January 2022 accrual window.

Outcome Variables

Data on the use of potentially avoidable, high-cost, or low-value health services and select metrics of appropriate care were extracted from the clinical records for the period spanning 6 months before and 6 months after each patient’s baseline date. Specific indicators included unplanned all-cause hospital admissions, potentially avoidable all-cause emergency department use, all-cause excess days in acute care (EDAC) within 30 days following hospital discharge, and 7-day readmissions. Among patients with advanced cancer, the following disease-specific indicators were also assessed: hospital admissions and emergency department visits for patients receiving outpatient chemotherapy, use of a triage clinic, completion of an advance directive, and any hospice use. Among patients with CKD, we also assessed the following additional indicators: CKD-related emergency department or hospital inpatient use and progression from CKD stage III to stage IV, stage IV to stage V, or stage III to stage V.

Statistical Analyses

DiD Framework

We used a DiD approach to assess changes in the use of high-cost health services and select metrics of appropriate care between patients in the dashboard groups and those in the comparison groups. All analyses were run separately for each disease cohort (advanced cancer and CKD) to account for their distinct clinical trajectories and use patterns. Health services use in the 6 months before the dashboard intervention were compared with use during the 6 months after the intervention, with the following equation:

y = β₀ + β₁ ∙ Time + β₂ ∙ Treated + β₃ ∙ (Time × Treated) + β₄ ∙ Covariates + ε

An interaction term for intervention group (“treated”) and time period (“time”) was included to test whether changes from the preintervention to postintervention periods differed between the dashboard and comparison groups. A statistically significant effect for the time period × intervention group interaction term (β₃) would suggest that the dashboard intervention is associated with differential health services use. The DiD models were estimated with Huber-White cluster-robust SEs that correct for heteroskedasticity, account for paired observations within patients, and cluster at the health care provider level to absorb unmeasured health care provider–level confounding [].

Propensity Scores and Inverse-Propensity Weighting

A valid DiD estimate rests on the parallel trends assumption—that in the absence of the intervention, average outcomes in the dashboard and comparison groups would have evolved similarly over time. Because our dataset included a single preintervention measurement for each outcome, we could not empirically test for parallel preperiod slopes. Instead, we increased the plausibility of a conditional parallel trends assumption by ensuring that the two groups were closely matched on observed baseline characteristics. Specifically, we estimated propensity scores [,] using a logistic regression model that included race, ethnicity, age, sex, insurance category, Charlson Comorbidity Index, baseline encounter date, median household income, and baseline health services use (number of observation admissions, number of outpatient encounters, and number of immediate urgent care encounters). Median household income, used as a proxy for socioeconomic status, was obtained from 5-digit residential zip codes in the Social Determinants of Health Database from the Agency for Healthcare Research and Quality []. Cancer type was added as a covariate to the advanced cancer propensity score model, and CKD stage was included in the CKD propensity score model. Dashboard patients received a weight equal to 1/(propensity score), whereas comparison patients were weighted as 1/(1 – propensity score). Weights greater than 10 were truncated to reduce the influence of outliers. The weighted analysis, therefore, estimated the average treatment effect on the treated (ATT).

Primary Model: Weighted Linear Probability DiD

We chose a linear probability model for ease of interpretation. The resulting β coefficients reflect absolute percentage point changes (eg, β=–0.05 implies a 5–percentage point reduction in risk for the dashboard group relative to the comparison group). Cancer type (advanced cancer cohort) or CKD stage (CKD cohort) was included as a fixed effect. Hospice use and CKD progression were observed only after the intervention; these outcomes were analyzed with single period–weighted linear probability models that omitted the period variable. Unadjusted models are reported in and .

Robustness for Low-Prevalence Outcomes

Some outcomes (eg, 7-day admission) have prevalences less than 20%. We, therefore, reestimated each model with the same inverse propensity weights using a logistic DiD model; the exponentiated interaction coefficient is reported as the ATT ratio-in–odds ratios (ROR). Linear ATT and logit ATT RORs are presented in the Results section, and the two specifications produce directionally and statistically consistent results. For very low sample prevalence (<10%), we additionally applied the Firth penalized likelihood method to mitigate small sample bias () []. For readers interested in population-level effects, a set of inverse propensity–weighted linear probability models estimating the average treatment effect in the entire study population is also provided in and .

Software and Packages

All statistical analyses were conducted in R (version 4.2.1; R Foundation for Statistical Computing) using sandwich 3.0.2 (robust variance) and WeightIt 1.4.0 (inverse propensity score weighting).

Hypothesis

We hypothesized that patients in the dashboard group would have fewer unplanned all-cause hospital admissions, fewer EDACs, and lower 7-day readmission rates than patients in the comparison cohort. For the cancer dashboard group, we anticipated higher rates of oncology triage clinic visits, advance directive completion, and hospice use, with a reduced likelihood of chemotherapy within the last 14 days of life. For the CKD dashboard group, we expected a decrease in emergency-start dialysis, CKD-related emergency department or inpatient use, and slower progression of CKD stages.

Study Population

Of the 748 patients enrolled in the dashboard study, 284 patients with advanced cancer and 365 patients with CKD completed the baseline questionnaires and composed the dashboard cohorts (). The comparison cohorts consisted of 917 patients with advanced cancer and 2137 patients with CKD who met the eligibility criteria but were not exposed to the dashboard. Before weighting, several baseline characteristics differed statistically between the dashboard and comparison groups ( and ). For example, the patients with advanced cancer in the dashboard group had more comorbidities (mean Charlson Comorbidity Index 8.62, SD 3.22, vs 6.93, SD 3.34) and were more often treated for lung cancer (191/284, 67.3% vs 176/917, 19.2%). Among patients with CKD, there were significant differences between the dashboard and comparison groups in CKD stage (P=0.005) and in the number of inpatient (P<0.001) and outpatient encounters (P<0.001).

‎

Figure 1. Study flowchart of dashboard and comparison group selection. CKD: chronic kidney disease.

Table 1. Cancer cohort: comparisons of demographic characteristics, previous health care use, and comorbidities between dashboard and comparison groups.

		Unweighted							Weighted^a
		Dashboard (n=284)	Comparison (n=917)	SMD^b,c		P value		Dashboard		Comparison	SMD^c		P value
Race, n (%)					0.130		.05					0.067		.79
	White	189 (66.5)	628 (68.5)					68.8		68.2
	Black	46 (16.2)	109 (11.9)					13.5		12.6
	Declined to answer	17 (6.0)	61 (6.7)					6.9		6.5
	Other	32 (11.3)	119 (13.0)					10.7		12.7
Ethnicity, n (%)					0.186		.002					0.090		.50
	Non-Hispanic	253 (89.1)	774 (84.4)					82.2		85.3
	Declined to answer	23 (8.1)	82 (8.9)					10.2		9.0
	Hispanic	8 (2.8)	61 (6.7)					7.6		5.7
Charlson Comorbidity Index, mean (SD)		8.62 (3.22)	6.93 (3.34)	0.52		<.001		7.59 (3.23)		7.40 (3.54)	0.057		.38
Age (years), mean (SD)		63.12 (12.84)	62.04 (12.66)	0.085		.08		63.37 (12.49)		62.48 (12.38)	0.072		.25
Insurance, n (%)					0.194		.002					0.111		.34
	Commercial	135 (47.5)	480 (52.3)					51.5		51.5
	Medicaid	15 (5.3)	74 (8.1)					5.1		7.1
	Medicare	134 (47.2)	360 (39.3)					43.4		41.2
	Uninsured	0 (0.0)	3 (0.3)					0.0		0.2
Male, n (%)		130 (45.8)	476 (51.9)	0.123		.01		48.1		50.4	0.046		.49
Lung cancer, n (%)		191 (67.3)	176 (19.2)	1.109		<.001		32.9		31.4	0.032		.58
Emergency encounters (n), mean (SD)^d		1.15 (1.72)	0.83 (1.48)	0.203		<.001		1.15 (1.68)		0.92 (1.54)	0.146		.03
Observation hospital admissions (n), mean (SD)^d		0.20 (0.55)	0.18 (0.54)	0.038		.42		0.27 (0.72)		0.19 (0.55)	0.134		.10
Inpatient encounters (n), mean (SD)^d		0.78 (1.26)	0.59 (1.04)	0.167		<.001		0.71 (1.22)		0.62 (1.08)	0.074		.27
Immediate urgent care encounters (n), mean (SD)^d		0.54 (1.12)	0.37 (0.98)	0.153		.001		0.53 (1.15)		0.43 (1.07)	0.094		.17
Outpatient encounters (n), mean (SD)^d		25.44 (18.69)	14.98 (15.41)	0.611		<.001		20.42 (14.64)		17.72 (17.32)	0.168		.002
Median household income (US $), mean (SD)		85,720 (32,862)	86,292 (31,095)	0.179		.71		85,285 (32,921)		85,873 (30,875)	0.018		.79

^aThe sum of weights for the dashboard group was 1135. The sum of weights for the comparison group was 1212.45. Previous health care use indicates health care services used during the 12 months prior to the baseline assessment.

^bSMD: standardized mean difference.

^cSMD quantifies the difference in a covariate’s mean values between groups, scaled by the pooled SD. While SMD values closer to 0 suggest better balance, values over 0.1 may indicate potential differences. In this study, most covariates demonstrated good balance after weighting, although a small number retained statistical significance at P<.05. To mitigate potential residual differences, the difference-in-differences outcome model included unit and time fixed effects and controlled for all baseline covariates regardless of their P values.

^dEncounters that occurred 12 months prior to baseline were included.

Table 2. Chronic kidney disease (CKD) cohort: comparisons of demographic characteristics, previous health care use, and comorbidities between the dashboard and comparison groups.

		Unweighted							Weighted^a
		Dashboard (n=365)	Comparison (n=2137)	SMD^b,c		P value		Dashboard		Comparison	SMD^c		P value
Race, n (%)					0.092		.19					0.050		.75
	White	183 (50.1)	1036 (48.5)					46.6		48.6
	Black	120 (32.9)	674 (31.5)					33.8		31.8
	Declined to answer	15 (4.1)	125 (5.8)					6.0		5.6
	Other	47 (12.9)	302 (14.1)					13.6		13.9
Ethnicity, n (%)					0.101		.05					0.024		.87
	Non-Hispanic	312 (85.5)	1753 (82.0)					81.6		82.5
	Declined to answer	19 (5.2)	121 (5.7)					6.0		5.6
	Hispanic	34 (9.3)	263 (12.3)					12.4		11.9
Charlson Comorbidity Index, mean (SD)		8.38 (3.79)	7.73 (3.69)	0.173		<.001		7.85 (3.65)		7.82 (3.81)	0.008		.85
Age (years), mean (SD)		64.31 (14.10)	63.46 (15.97)	0.056		.18		64.08 (14.42)		63.54 (15.90)	0.036		.40
Insurance, n (%)					0.058		.72					0.055		.55
	Commercial	131 (35.9)	744 (34.8)					34.2		35.0
	Medicaid	33 (9.0)	192 (9.0)					9.6		9.0
	Medicare	201 (55.1)	1198 (56.1)					56.2		56.0
	Uninsured	0 (0.0)	3 (0.1)					0.1		0.0
Male, n (%)		209 (57.3)	1066 (49.9)	0.148		<.001		51.7		50.9	0.017		.70
Emergency encounters (n), mean (SD)^d		1.58 (2.23)	1.37 (2.60)	0.086		.04		1.62 (2.48)		1.40 (2.63)	0.087		.15
Observational encounters (n), mean (SD)^d		0.38 (0.71)	0.29 (0.70)	0.126		.002		0.32 (0.66)		0.31 (0.71)	0.025		.55
Inpatient encounters (n), mean (SD)^d		1.05 (1.51)	0.72 (1.35)	0.229		<.001		0.80 (1.25)		0.77 (1.41)	0.021		.62
Immediate urgent care encounters (n), mean (SD)^d		0.73 (1.63)	0.64 (2.03)	0.046		.28		0.69 (1.60)		0.66 (2.07)	0.019		.51
Outpatient hospital admissions (n), mean (SD)^d		20.69 (15.39)	15.78 (14.31)	0.331		<.001		17.10 (13.08)		16.73 (16.44)	0.025		.51
Median household income (US $), mean (SD)		77,925 (30,283)	77,432 (31,131)	0.016		.69		77,401.71 (30,239)		77,505.09 (31,146)	0.034		.94
CKD stage, n (%)					0.129		.005					0.037		.68
	Stage III	54.8	61.1					58.3		60.1
	Stage IV	30.1	26.2					27.7		26.7
	Stage V	15.1	12.7					14.0		13.2

^aThe sum of weights for the dashboard group was 2504.1. The sum of weights for the comparison group was 2504.85. Previous health care use indicates health care services used during the 12 months prior to the baseline assessment.

^bSMD: standardized mean difference.

^cSMD quantifies the difference in a covariate’s mean values between groups, scaled by the pooled SD. While SMD values closer to 0 suggest better balance, values over 0.1 may indicate potential differences. In this study, P values were also assessed, demonstrating minimal statistical differences between groups, even for covariates with SMD values close to 0.1. To mitigate potential residual differences, the difference-in-differences outcome model included unit and time fixed effects and controlled for all baseline covariates regardless of their P values.

^dEncounters that occurred 12 months prior to baseline were included.

After applying inverse propensity weighting, the standardized mean difference was less than 0.10 for every variable except outpatient encounter volume in the cancer cohort. Accordingly, the covariates were included as fixed effects in the weighted DiD models to further control for potential confounding and improve comparability ( and ) [,].

Association Between Dashboard Use and High-Cost Services Use

Advanced Cancer Cohort

In weighted DiD models, dashboard exposure was not associated with changes in unplanned all-cause admission rates (ATT: β=–0.017, 95% CI –0.107 to 0.072; ROR 0.89, 95% CI 0.46-1.72; ). In contrast, dashboard exposure was associated with a 4–percentage point increase in EDACs relative to the comparison group (ATT: β=0.040, 95% CI –0.001 to 0.089), although the corresponding odds ratio was not significant (ROR 5.84, 95% CI 0.89-38.42). Dashboard users also experienced a 3.7–percentage point rise in the 7-day readmission rate (ATT: β=0.037, 95% CI 0.008-0.066), with a significant increase in odds (Firth-adjusted ROR 8.58, 95% CI 2.28-32.32). Chart review confirmed that 93% of these early readmissions were scheduled by clinicians, suggesting intentional proactive care rather than unplanned deterioration.

Table 3. Cancer: propensity score–weighted difference-in-differences results^a.

Health services type	Dashboard group (n=284), n (%)			Comparison group (n=917), n (%)			Linear ATT^b, b (95% CI)		Logit ATT, ROR^c (95% CI)
	Before	After	Before		After
Unplanned all-cause hospital admissions	57 (20.1)	63 (22.1)	157 (17.1)		244 (26.7)	–0.017 (–0.107 to 0.072)		0.892 (0.463 to 1.720)
EDAC^d within 30 days of hospital discharge	116 (40.8)	129 (45.4)	143 (15.6)		219 (23.9)	0.040 (–0.001 to 0.089)		5.838 (0.887 to 38.424)
7-day hospital readmissions	4 (1.4)	14 (4.9)	4 (0.4)		5 (0.5)	0.037 (0.008 to 0.066)		9.544 (1.339 to 60.192)
Hospital admissions and ED^e visits for patients receiving outpatient chemotherapy	30 (10.6)	54 (19.0)	43 (4.7)		161 (17.6)	–0.014 (–0.102 to 0.074)		0.351 (0.163 to 0.753)
Oncology triage clinic use	40 (14.1)	56 (19.7)	32 (3.4)		80 (8.7)	0.047 (–0.031 to 0.125)		0.674 (0.322 to 1.412)
Completion of an advanced directive	5 (1.7)	5 (1.7)	11 (1.2)		33 (3.6)	–0.009 (–0.039 to 0.020)		0.245 (0.048 to 1.247)
Hospice use^f	—^g	11/27 (40.7)	—		32/65 (49.2)	0.203 (–0.049 to 0.454)		2.837 (0.755 to 10.662)

^aAll coefficients are the ATT (b) obtained with inverse propensity-weighted difference-in-differences modes. Linear ATT is the treatment-effect coefficient from the weighted linear probability DiD; logit ATT ROR is the corresponding ratio-in–odds ratios from a weighted logistic regression fit to the identical analytic sample. Both models adjust for all baseline covariates included in the propensity score specification to minimize residual confounding: race, ethnicity, age, sex, insurance category, Charlson Comorbidity Index, cancer type, baseline use encounter date, median household income (zip code level), and baseline use counts (emergency, observation, inpatient, immediate/urgent care, and outpatient encounters). Time and time × treated interaction terms were excluded from the regression analyses.

^bATT: average treatment effect on the treated.

^cROR: ratio-in–odds ratios.

^dEDAC: excess days in acute care.

^eED: emergency department.

^fFor hospice use, the denominator is restricted to patients who died during the study period who received care from a participating study physician.

^gNot applicable.

Notably, the pattern reversed among patients receiving outpatient chemotherapy. The dashboard intervention was associated with a significant 65% reduction in the odds of acute care use (hospital admission or emergency department visit) in this subgroup (ROR 0.35, 95% CI 0.16-0.75), although the linear DiD estimate did not reach statistical significance. Conversely, completion of advance directives declined among dashboard users (Firth-adjusted ROR 0.25, 95% CI 0.10-0.67). No statistically significant associations were observed for oncology triage visits or hospice use.

CKD Cohort

In the CKD cohort, dashboard exposure was not associated with any of the prespecified outcomes, including unplanned admissions, EDACs, 7-day readmissions, CKD-related acute use, or CKD progression, under either the linear ATT β or Firth-adjusted logit ATT ROR specification ().

Table 4. Chronic kidney disease (CKD): propensity score–weighted difference-in-differences results^a.

Health services type	Dashboard group (n=365), n (%)		Comparison group (n=2137), n (%)		Linear ATT^b, b (95% CI)	Logit ATT, ROR^c (95% CI)
	Before	After	Before	After
Unplanned all-cause hospital admissions	112 (30.7)	94 (25.8)	412 (19.3)	385 (18.0)	–0.010 (–0.073 to 0.053)	0.879 (0.565 to 1.368)
EDAC^d within 30 days of hospital discharge	20 (5.4)	22 (6.0)	32 (1.5)	23 (1.1)	0.001 (–0.035 to 0.036)	1.300 (0.491 to 3.442)
7-day hospital readmissions	7 (1.9)	9 (2.4)	12 (0.6)	10 (0.5)	0.006 (–0.016 to 0.028)	1.591 (0.364 to 6.950)
CKD-related ED^e or inpatient use	128 (35.1)	112 (30.7)	483 (22.6)	523 (24.5)	–0.050 (–0.118 to 0.018)	0.752 (0.502 to 1.126)
Progression from CKD stage III to IV, stage IV to V, and stage III to stage V	—^f	31 (8.4)	—	334 (15.6)	–0.002 (–0.034 to 0.029)	1.073 (0.695 to 1.655)

^aAll coefficients are the ATT obtained with inverse propensity weighted difference-in-differences modes. Linear ATT (b) is the treatment effect coefficient from the weighted linear probability difference in differences; logit ATT ROR is the corresponding ratio-in–odds ratios from a weighted logistic regression fit to the identical analytic sample. Both models adjust for all baseline covariates included in the propensity score specification to minimize residual confounding: race, ethnicity, age, sex, insurance category, Charlson Comorbidity Index, CKD stage, baseline encounter date, median household income (zip code level), and baseline use counts (emergency, observation, inpatient, immediate/urgent care, and outpatient encounters). Time and time × treated interaction terms were excluded from the regression analyses.

^bATT: average treatment effect on the treated.

^cROR: ratio-in–odds ratios.

^dEDAC: excess days in acute care.

^eED: emergency department.

^fNot applicable.

Principal Findings

Using a propensity score–weighted DiD design, we found that the co-designed PRO dashboard had disease-specific and mixed effects on use of high-cost services. For patients with advanced cancer, dashboard use was associated with fewer acute encounters during outpatient chemotherapy (a 65% reduction in odds), yet dashboard use also coincided with increased planned 7-day readmissions and a modest rise in excess days in acute care. No other use outcomes changed, and no effects were detected in the CKD cohort.

Comparison With Prior Work

Previous randomized symptom monitoring trials in oncology have reported 30% to 50% reductions in emergency department visits and hospitalizations when PRO alerts triggered nurse triage or oncologist feedback [,]. Our observed 65% reduction in odds of acute care encounters related to outpatient chemotherapy aligns with these findings, suggesting that PRO-informed dashboards can be effective in real-world clinical settings, not just trials. An increase in 7-day readmission rates mirrors patterns seen in heart failure programs, where early, proactive readmissions are reframed as planned care. This suggests that the dashboard may support clinician-directed early symptom management.

We also observed a significant decrease in advance directive completion among dashboard users in the advanced cancer cohort. This may reflect a shift of clinical attention toward pressing symptoms, similar to a US Department of Veterans Affairs trial where increased planning discussions did not improve alignment with patient preferences []. This highlights how even well-designed dashboards can induce unintended consequences, underscoring the need for thoughtful integration into care processes.

For CKD, our null findings align with a systematic review indicating that stand-alone SDM tools rarely impact high-cost use metrics []. Without concurrent disease management supports or stronger engagement by clinicians and patients, dashboards may be insufficient to change care trajectories in slowly progressive conditions. Current evidence, therefore, remains mixed on whether SDM interventions alone can consistently curb costly service use.

Implications for SDM Tools

Patient engagement in SDM is shaped by multiple forces. While financial strain can sharpen patients’ desire to weigh costs against benefits, the general shift toward patient-centered care, greater transparency in outcomes, and heightened emphasis on quality of life also motivate participatory decisions []. Our dashboard, which pairs PRO trends with open-ended prompts on the goals of care, may have resonated most strongly with oncology patients because acute toxicity and quality of life trade-offs are immediate and visible during chemotherapy. CKD trajectories are typically slower; without real-time laboratory or symptom triggers, the dashboard information may have seemed less actionable to nephrology teams, resulting in lower engagement and impact in that setting.

Cancer-Type Heterogeneity

The advanced cancer cohort comprised patients with lung and gastrointestinal malignancies. Although both subgroups face heavy symptom burdens, needs can diverge: patients with lung cancer report dyspnea and cough as dominant concerns, whereas patients with gastrointestinal cancer often prioritize nausea, appetite, and bowel symptoms [-]. The dashboard displayed all PROMIS domains identically, which may have diluted its relevance for patients whose dominant symptoms were not being addressed in the clinic. Future iterations could include cancer-specific symptom widgets or algorithmic highlighting of domain scores most relevant to each cancer type to increase salience for both patients and health care providers.

Strengths and Limitations

The study’s key strengths are its evaluation in routine clinical practice across two distinct specialties (oncology and nephrology), use of rigorous inverse propensity weighting that achieved robust covariate balance, and parallel reporting of additive (percentage point) and multiplicative (ROR) effects, which allows findings to be interpreted consistently across outcomes with different prevalence rates.

There are several limitations. First, all use data were drawn from a single US academic health network; encounters that occurred elsewhere were unseen, and results may not generalize to community or non-US settings. Second, patients were not randomly assigned to the dashboard intervention, which limits our ability to make causal claims about the effect of dashboard use. Although our weighting approach improved the balance of patient characteristics between the intervention and comparison groups, residual confounding from unmeasured factors (eg, digital literacy) could remain. Third, dashboard patients exhibited higher baseline use, suggesting higher initial health care needs; the analytical approach mitigated but may not have fully eliminated this imbalance, potentially biasing postintervention contrasts.

Conceptual Implications for Dashboard Design

Our findings reinforce a fundamental principle of user-centered, participatory design: a dashboard’s value depends on how well it integrates with the downstream clinical workflow. In our advanced cancer cohort, the dashboard was associated with fewer chemotherapy-related acute care encounters, suggesting that when clinicians have a clear, rapid way to respond to symptom data, visualizing those data in a dashboard may avert costly health services use. In contrast, the absence of any effect among patients with CKD may imply that, without an equally responsive care pathway, a stand-alone dashboard cannot produce meaningful change.

This observation aligns with evidence from a recent participatory design intervention in surgical ward rounds, where stakeholders confirmed that successful implementation hinged on both tool usability and system readiness, including routines, coordination, and technology infrastructure []. Just as that study revealed the importance of aligning design with contextual factors and cultural norms, our dashboard’s impact depended on having disease-specific support pathways in place.

Future versions should, therefore, be co-designed not only around what information is displayed but also around disease-specific response workflows (eg, automated alerts routed to the appropriate clinician, or prompts that trigger standing orders) [].

Conclusions

While a co-designed dashboard may help reduce high-cost health services use and improve select care metrics for patients with advanced cancer, the dashboard appears to be less effective for patients with CKD. As the first study on an SDM intervention and its impact on health services use for these groups, the results were mixed. More research is needed to fully understand the impact of co-designed dashboards on improving emotional, clinical, and use outcomes.

We would like to extend our gratitude to the patients and clinicians involved in this study for their contribution and collaboration toward improving person-centered care. Their insights and expertise were instrumental to our research. OpenAI’s GPT-4o was used to support code analysis and grammatical editing of the manuscript. All artificial intelligence–generated content was carefully reviewed and verified by the authors to ensure accuracy and originality.

We gratefully acknowledge the financial support provided by the Peterson Center on Healthcare (principal investigator DC).

The data supporting these study findings were derived from electronic health records within the participating health care system and are not publicly available due to privacy and confidentiality restrictions.

SA and NJ conducted the statistical analyses and drafted the initial manuscript. All authors conceived and designed the study. All authors reviewed and approved the manuscript.

None declared.

Edited by N Cahill; submitted 21.Dec.2024; peer-reviewed by T Brown, LR Guo; comments to author 05.May.2025; revised version received 25.Jul.2025; accepted 29.Sep.2025; published 21.Nov.2025.

©Saki Amagai, Alexandra Harris, Nisha Mohindra, Sheetal Kircher, Jeffrey A Linder, Vikram Aggarwal, John D Peipert, Katy Bedjeti, Quan Mai, Cynthia Barnard, Ava Coughlin, Mary O’Connor, Victoria Morken, David Cella, Neil Jordan. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 21.Nov.2025.

Currency	19-Nov 2025	20-Nov 2025	21-Nov 2025	Change +/–
USD	280.6616	280.6518	280.6229	0.0289
EUR	325.1325	323.2969	323.8669	-0.5700
GBP	368.9017	366.8400	367.0688	-0.2288
AUD	182.1915	181.6940	180.7633	0.9307
MYR	67.6864	67.4806	67.6689	-0.1883
CNY	39.4778	39.4393	39.4527	-0.0134
CAD	200.5514	199.6314	199.0445	-0.5869
AED	76.4121	76.4178	76.4047	0.0131
SAR	74.8391	74.8325	74.8208	0.0117

Category: 3. Business

Introduction

Methods

Study Design

Eligibility Criteria

Data Sources, Search Strategy, and Study Selection

Data Extraction

Data Analysis

Patient and Public Involvement

Results

Selection of Sources of Evidence

General Characteristics of the Included Studies

Characteristics of Privacy Protection

Discussion

Main Findings

Strengths and Limitations

Implications for Research and Practice

Considerations in Research Design

Considerations in Research Implementation

Considerations in Research Reporting

Conclusions

Introduction

Methods

Dashboard Design, Content, and Integration With Clinical Workflow

Study Design and Location

Ethical Considerations

Participants and Eligibility Criteria

Outcome Variables

Statistical Analyses

DiD Framework

Propensity Scores and Inverse-Propensity Weighting

Primary Model: Weighted Linear Probability DiD

Robustness for Low-Prevalence Outcomes

Software and Packages

Hypothesis

Results

Study Population

Association Between Dashboard Use and High-Cost Services Use

Advanced Cancer Cohort

CKD Cohort

Discussion

Principal Findings

Comparison With Prior Work

Implications for SDM Tools

Cancer-Type Heterogeneity

Strengths and Limitations

Conceptual Implications for Dashboard Design

Conclusions

1. Hero to zero

2. Prediction market

Get Morning Squawk directly in your inbox

3. Better than yours

4. AI in D.C.

5. Flight fight

The Daily Dividend

Other currencies