Category: 3. Business

Introduction

What Do We Understand About Plant-Derived Exosome-Like Nanovesicles?

In recent years, Plant-derived exosome-like nanoparticles (PELNs) have attracted increasing attention as natural nanocarriers for biomedical applications. While mammalian-derived exosomes also demonstrate therapeutic potential, their clinical translation faces several challenges, including the risk of immune rejection, possible transmission of animal-borne pathogens, ethical concerns regarding the use of animal-derived materials, animal welfare considerations, low production yields, and the high cost of establishing large-scale culture systems. In contrast, PELNs are abundant and are typically derived from fruits, vegetables, and medicinal herbs, making them sustainable and readily available.¹ They carry unique bioactive cargos such as plant-specific proteins, lipids, nucleic acids, and microRNAs(miRNAs), offering them with distinct functional properties and broad translational promise.² Moreover, plant materials are easier to obtain, more economical to process, and simpler to store and transport, while avoiding the ethical concerns often associated with animal-derived exosomes in drug development.³

Currently, PELNs are primarily isolated using ultracentrifugation, ultrafiltration centrifugation, and density gradient centrifugation.⁴ However, variations in these protocols often result in substantial differences in yield, purity, and biological activity. Compared with size exclusion chromatography, ultracentrifugation allows the processing of larger sample volumes and achieves higher yields. In contrast to the more economical polymer precipitation method, it results in fewer co-precipitated impurities. Although density gradient centrifugation generally provides higher purity, both ultrafiltration centrifugation and ultracentrifugation are more practical for large-scale preparations, with ultracentrifugation often preferred for its balance of yield and feasibility (Table 1). ^2,4–6 Recent efforts have therefore focused on developing scalable isolation strategies that optimize yield and purity while preserving the functional integrity of PELNs.

Table 1 Comparison of Conventional Separation Techniques for PELNs

In the characterization of PELNs, biochemical profiling serves as a critical step in distinguishing them from other types of extracellular vesicles, particularly functional microvesicles.² Molecular characterization is commonly performed using Western blotting and flow cytometry. Potential markers for PELNs include surface proteins such as CD63,⁷ PEN1,⁸ TET8,^5,8 Exo70,⁵ TET3,⁵ Class I chitinase (PR-3) and Class I β-1,3-glucanase (PR-2).⁹ Internal proteins such as heat shock protein 70 (HSP70), glyceraldehyde-3-phosphate dehydrogenase (GAPDH), and S-adenosylhomocysteine hydrolase (SAHH) are also frequently reported.^5,8 Nucleic acids, particularly small RNAs, can be profiled using next-generation sequencing or qPCR. Lipidomic analysis via mass spectrometry has revealed that PELNs possess lipid bilayers primarily composed of phosphatidylcholine and phosphatidylethanolamine. Notably, the lipid composition varies among PELNs derived from different plant sources.⁷ Phosphatidic acid, in particular, is a dominant lipid species that plays a key role in the uptake and absorption of PELNs by recipient cells⁸ (Figure 1).

Figure 1 Structural and molecular composition of PELNs. This figure illustrates a PELN, typically 50–200 nm in diameter, with a spherical or cup-shaped morphology and a lipid bilayer membrane. Characteristic surface markers include CD63, PEN1, TET8, TET3, Exo70, Class I chitinase (PR-3), and Class I β-1,3-glucanase (PR-2). Internal contents of PELNs consist of cytosolic proteins such as HSP70, GAPDH, nucleic acids (miRNA, RNA), lipids, and other biologically active constituents. The membrane composition mainly includes phosphatidylcholine (PC), phosphatidylethanolamine (PE), and phosphatidic acid (PA), which are critical for vesicle stability and cellular uptake. The figure also includes a symbolic legend indicating the molecular components. (By Figdraw).

Due to their low immunogenicity, excellent biocompatibility, inherent targeting capacity, and suitability for surface engineering, PELNs have been widely explored in drug delivery, diagnostics, and therapeutic intervention.^5,10 They have demonstrated promising effects across diverse disease models, including inflammation, oxidative stress, cancer, wound healing,⁸ immune regulation, neuroprotection, metabolic modulation, cardiovascular protection, gut homeostasis, osteoporosis, muscle atrophy, and premature ovarian failure. Notably, PELNs are compatible with multiple administration routes, including oral, intravenous, intratracheal, intranasal, and topical delivery.¹¹ This review therefore provides a comprehensive overview of therapeutic applications and signaling mechanisms associated with PELNs, offering insights to guide future translational research and clinical development.

The Key Therapeutic Applications of Plant-Derived Exosome-Like Nanoparticles

Among the various biomolecules encapsulated in PELNs, miRNAs are key post-transcriptional regulators of gene expression. Their therapeutic potential lies in their ability to mediate cross-kingdom communication, thereby increasing the diversity of miRNAs in mammalian cells and exerting multi-target effects.^12,13 PELNs can protect miRNAs from degradation in the gastrointestinal tract while maintaining specific concentrations. Studies suggest that PELNs contain hundreds of miRNAs, and a single miRNA can target hundreds of mRNAs. Thus, when PELNs levels reach a certain baseline, they may produce significant regulatory effects.¹⁴

For example, ginseng-derived plant exosomes carry mtr-miR159 and deliver it into bone marrow mesenchymal stem cells. This upregulates Tmem100 and activates the PI3K/Akt signaling pathway, promoting neural differentiation and enhancing peripheral nerve regeneration in a rat model of peripheral nerve injury.¹⁵ In another study, ginseng-derived exosome-like nanoparticles delivered their endogenous vvi-miR396b and ptc-miR396f into glioma cells, silencing the oncogenes c-MYC and BCL2, effectively inhibiting tumor growth and achieving efficient blood-brain barrier penetration.¹⁶

Similar to miRNA, small interfering RNA (siRNA) is a double-stranded RNA molecule approximately 20–25 nucleotides in length. It can bind perfectly to the target mRNA and induce its degradation, leading to specific gene silencing. siRNA has important potential for precision therapy, especially in cancer treatment. A typical example is ginger-derived exosome-like nanoparticles (GELNs), which deliver Bcl2 siRNA into tumor cells. By silencing the anti-apoptotic gene Bcl2, they activate the apoptosis pathway in cancer cells and significantly suppress tumor growth in a mouse breast cancer model.¹⁷

PELNs have recently been shown to influence cell fate, inflammatory responses, oxidative stress, tissue repair, metabolic regulation, and tumor immunity through diverse molecular mechanisms.¹⁸ The following studies reveal their considerable potential in disease treatment.

PELNs can regulate cell proliferation, apoptosis, differentiation, and stemness maintenance through multiple signaling pathways and key molecules, thereby contributing to tissue repair, disease therapy, and regenerative medicine. In terms of cell proliferation, PELNs from Momordica charantia are a typical example. They activate the PI3K/Akt and ERK signaling pathways, upregulate PCNA, Cyclin D1, Cyclin B1, and Ki-67, promote cell cycle progression, and enhance cell proliferation, which improves the repair capacity of cardiomyocytes after radiation injury.¹⁹ Regarding apoptosis, PELNs from Brucea javanica carry natural miRNAs (such as the let-7 family) that inhibit the PI3K/Akt/mTOR pathway while activating ROS/caspase-dependent apoptosis, leading to caspase-3 and PARP cleavage. This suppresses tumor cell survival and induces programmed cell death, highlighting the potential of plant exosomes in antitumor therapy.²⁰ In differentiation, PELNs from Panax ginseng activate the PI3K/Akt pathway through miRNAs, significantly upregulate Nestin, β3-tubulin, NGF, BDNF, and bFGF, and drive bone marrow mesenchymal stem cells to differentiate into neurons, providing new insights into neural repair and the treatment of neurodegenerative diseases.¹⁵ In stemness maintenance, PELNs from Grape inhibit GSK-3β activity, stabilize β-catenin nuclear translocation, and activate the Wnt/β-catenin pathway. This induces transcription factors such as c-Myc, Lgr5⁺, SOX2, Nanog, OCT4, and KLF4, which enhance the self-renewal and regeneration of intestinal stem cells.²¹ These studies indicate that PELNs regulate cell cycle factors, apoptosis pathways, differentiation markers, and stemness-related transcription factors, thus playing important roles in cell fate and opening new directions for tissue repair, antitumor therapy, and regenerative medicine.

PELNs also exhibit strong anti-inflammatory and immunomodulatory activities. PELNs from Panax notoginseng inhibit M1 macrophage polarization and promote M2 polarization, reducing TNF-α and IL-6 while increasing IL-10, thereby alleviating inflammation.²² PELNs from Garlic suppress the TLR4/NF-κB pathway, downregulate inflammatory cytokines such as IL-6 and TNF-α, and enhance the tight junction protein ZO-1 to maintain intestinal barrier integrity.²³ PELNs from Broccoli mainly act through the AMPK pathway, promoting tolerogenic dendritic cells and Tregs to restore immune homeostasis.²⁴ These findings suggest that PELNs regulate immune cell phenotypes and cytokine levels through multiple pathways and hold therapeutic potential for inflammatory diseases.

In addition, PELNs demonstrate antioxidative potential. For example, PELNs from Mung bean sprouts activate the PI3K/Akt-Nrf2 pathway to upregulate HO-1 and SOD, and reduce oxidative stress.²⁵ PELNs from Carrot enhance HO-1 and NQO1 via the Nrf2/ARE pathway and decrease ROS production, improving cellular antioxidant defense.²⁶ PELNs from Ginger, which contain 6-Shogaol, also activate Nrf2 and further enhance the ability to scavenge free radicals.²⁷ These mechanisms show that PELNs can effectively strengthen antioxidant capacity, providing new approaches for preventing tissue injury and delaying aging.

In metabolic regulation, PELNs display broad effects. PELNs from Garlic upregulate GLP-1 and IRS1/2, enhance insulin signaling, and improve glucose utilization.²⁸ PELNs from Mung bean sprouts increase GLUT4 expression and decrease GSK-3β activity, promoting glucose uptake and glycogen synthesis and improving insulin resistance.²⁵ PELNs from Citrus limon suppress lipid metabolism genes such as ACACA, DDHD1, and DHCR24, reduce lipid synthesis, and induce tumor cell apoptosis.²⁹ These results indicate that PELNs can improve glucose metabolism, enhance insulin sensitivity, and regulate lipid metabolism, showing promise in the treatment of metabolic diseases.

In immune regulation and antitumor responses, PELNs demonstrate unique mechanisms. Exosomes from Artemisia annua contain plant mitochondrial DNA, which activates the cGAS-STING pathway, enhances IFN-I production, and promotes CD8⁺ T cell activation, thereby improving antitumor immunity.³⁰ PELNs from Catharanthus roseus act through the TNF-α/NF-κB/PU.1 axis to strengthen immune cell function and relieve chemotherapy-induced immunosuppression.³¹ PELNs from Panax ginseng activate TLR4 signaling, drive tumor-associated macrophages toward the M1 phenotype, and enhance local immune activity.³² These studies indicate that PELNs can regulate both innate and adaptive immunity, enhance antitumor responses, and provide new strategies for cancer immunotherapy.

PELNs are currently under clinical investigation for a variety of human diseases. Ongoing clinical trials are evaluating their therapeutic efficacy in the treatment of colorectal cancer (NCT01294072), head and neck cancer (NCT01668849), and IBD treatment (NCT04879810). Table 2 and Table 3 summarize the classification of PELN-based therapies according to disease types and the therapeutic drugs delivered by PELNs, respectively.³³

Table 2 Classification of PELNs Therapies by Disease Types

Table 3 Therapeutic Drugs Delivered by PELNs

Effects of Plant-Derived Exosome-Like Nanoparticles on Disease-Associated Signaling Pathways

PELNs exert therapeutic effects by modulating multiple critical signaling pathways, including PI3K/Akt, NF-κB, Wnt, AMPK, MAPK, the NLRP3 inflammasome, cGAS/STING, and Nrf2/ARE. Through these regulatory axes, PELNs influence key biological processes such as metabolic homeostasis, anti-inflammation, antioxidation, wound healing, neuroprotection, and tumor suppression, thereby offering therapeutic promise in diverse pathological conditions, including diabetes, neurodegenerative diseases, cardiovascular disorders, inflammatory diseases, and cancer.

PELNs activate PI3K/Akt pathway to promote cell survival, proliferation, and metabolic regulation. In metabolic diseases such as diabetes, PELNs enhance Glucose Transporter Type 4 (GLUT4) expression via the PI3K/Akt pathway, thereby improving insulin resistance.²⁵ In neuroprotection (eg, neurodegeneration, ischemic stroke, and ischemia-reperfusion injury), they inhibit apoptosis and maintain blood-brain barrier (BBB) integrity.^22,77,78 This pathway also facilitates wound healing by promoting skin cell proliferation, migration, extracellular matrix secretion, and angiogenesis.⁶⁷ In tumors, PELNs modulate cancer cell survival, proliferation, and metabolism while inhibiting invasion and metastasis.^20,58,59

NF-κB pathway is primarily involved in regulating inflammation, immune responses, and cell survival. In inflammatory diseases (eg, colitis), PELNs downregulate pro-inflammatory cytokines such as TNF-α and IL-6, alleviating inflammation.²³ In bone metabolism disorders (eg, osteoporosis), they inhibit osteoclast activation to reduce bone loss.⁸³ They also enhance immune function (eg, post-chemotherapy immunomodulation) by activating lymphocytes and macrophages,³¹ and contribute to anti-aging effects in skin by promoting collagen expression.⁷²

Wnt signaling pathway regulates cell proliferation, differentiation, and tissue homeostasis. PELNs promote intestinal stem cell proliferation and differentiation via Wnt/TCF4 activation, thus supporting intestinal repair.¹⁰⁴ In inflammatory conditions like colitis, they modulate neural stem cell differentiation in the intestine to enhance regenerative capacity.²¹

AMPK pathway is a master regulator of cellular energy metabolism and homeostasis. In muscle atrophy, PELNs upregulate myogenesis-related factors, enhance metabolic activity, and improve mitochondrial function.⁸⁵ In inflammation (eg, colitis), they attenuate inflammation by suppressing pro-inflammatory cytokines and promoting anti-inflammatory mediators.²⁴

MAPK pathway governs cell proliferation, differentiation, stress responses, apoptosis, and inflammation. In inflammatory liver injury (eg, acetaminophen (APAP)-induced hepatotoxicity), PELNs inhibit phosphorylation of key proteins, reducing hepatocyte apoptosis and inflammation.⁹⁶ In neuroprotection and cardioprotection, they improve cell survival and prevent radiation-induced apoptosis.^19,77 Additionally, they promote tissue regeneration (eg, wound healing), bone remodeling (eg, osteoporosis),^67,82–84 and exert antitumor effects by suppressing proliferation, inducing apoptosis, and reducing tumor cell invasiveness.^29,58

NLRP3 inflammasome regulates innate immunity and the release of pro-inflammatory cytokines. In conditions such as hepatic injury, sepsis-induced acute lung injury, and ulcerative colitis, PELNs inhibit NLRP3 inflammasome assembly, reduce cytokine release, and mitigate inflammatory damage.^{35,42,44,50,105}

cGAS/STING pathway plays a crucial role in innate immunity, antiviral defense, and antitumor immunity. In metabolic disorders such as insulin resistance and type 2 diabetes, PELNs improve metabolic function by reducing inflammation and promoting insulin receptor substrate expression.^28,76 In tumor immunoregulation, they reshape macrophage phenotypes and enhance antitumor immunity, thereby suppressing tumor growth.³⁰

Nrf2/ARE pathway alleviates oxidative stress by upregulating antioxidant defenses. In neurodegenerative diseases (eg, Parkinson’s disease), PELNs reduce oxidative damage and enhance neuronal survival.²⁶ In cardiovascular diseases (eg, myocardial infarction) and inflammatory liver injury (eg, alcoholic fatty liver), they suppress ROS production and induce antioxidant enzymes such as HO-1 and NQO1, thereby reducing tissue injury.^{26,27,79,81,106}

Collectively, PELNs modulate diverse signaling pathways to regulate metabolism, inflammation, oxidative stress, tissue regeneration, and tumor progression, highlighting their broad clinical potential across multiple disease spectrums. (Figure 2).

Table 4 Summary of Signaling Pathways Affected by PELNs

Figure 2 Hierarchical representation of PELNs-regulated signaling pathways and associated diseases. This three-tier circular diagram illustrates the relationship between key signaling pathways modulated by PELNs, the major disease categories they influence, and specific pathological conditions. This three-tier circular figure illustrates the relationship between key signaling pathways modulated by plant-derived exosome-like nanoparticles (PELNs), the major disease categories they influence, and specific pathological conditions. Inner ring (core): Key signaling pathways involved in PELNs-mediated therapeutic effects, including PI3K/Akt, NF-κB, MAPK, AMPK, Wnt, NLRP3 inflammasome, cGAS/STING, Nrf2/ARE, among others. Middle ring: Broad disease categories influenced by the corresponding pathways, such as metabolic disorders, inflammatory diseases, neurodegenerative conditions, cardiovascular diseases, musculoskeletal disorders, cancers, and tissue regeneration. Outer ring: Representative diseases within each category (eg, diabetes, ulcerative colitis, ischemic stroke, myocardial infarction, osteoporosis, TNBC, etc.). The figure highlights the multifunctional regulatory roles of PELNs across diverse pathological contexts. (By Figdraw).

In addition to the major signaling pathways discussed above, several less common but biologically relevant pathways modulated by PELNs have also been identified and are comprehensively summarized in Table 4. With the continued elucidation of the molecular mechanisms by which PELNs regulate intracellular signaling, their application in precision drug delivery is expected to expand significantly. Owing to their low cytotoxicity, high biocompatibility, and minimal intrinsic immunogenicity, PELNs offer a unique therapeutic modality that integrates drug delivery, signaling modulation, and dynamic response to pathological stimuli. This multifaceted functionality enables a synergistic “delivery–regulation–therapy” strategy to enhance therapeutic efficacy. Furthermore, the inherent targeting capacity of PELNs, coupled with their surface modifiability, holds great promise for the development of intelligent drug delivery systems. Such systems would possess disease-site recognition, stimulus responsiveness, and controlled release capabilities, offering a more efficient, safe, and personalized treatment approach for chronic disorders, cancer, and inflammatory diseases.

Beyond signaling pathways, several bioactive molecules have been identified as mediators of PELN function. For example, Houttuynia cordata PELNs contain flavonoids such as luteolin,³⁵ ginger-derived PELNs carry 6-shogaol,²⁷ broccoli-derived PELNs deliver sulforaphane,²⁴ and Artemisia annua PELNs contain mitochondrial DNA,³⁰ engineered ginseng-derived ELNs are loaded with miR-182-5p,⁵⁰ tomato-derived PELNs carry miR164a/b-5p,⁸¹ ginseng-derived nanoparticles contain various miRNAs,¹⁵ Momordica charantia PELNs include miR-5266 and miR-5813,⁷⁸ and Brucea javanica PELNs contain functional miRNAs such as let-7.²⁰ These findings show more clearly which bioactive components of PELNs are responsible for their therapeutic effects.

Future Prospective

With the progress of research on PELNs in drug delivery and disease treatment, their potential as novel therapeutic tools is becoming increasingly evident. Current preclinical studies have demonstrated that PELNs possess low immunogenicity, favorable biocompatibility, and can be given through multiple administration routes. They have shown positive therapeutic effects in models of inflammation, cancer, cardiovascular disease, neurodegeneration, and metabolic disorders. Importantly, PELNs can not only serve as carriers for drugs and nucleic acids (eg, miRNA and siRNA), but also provide therapeutic benefits through their own bioactive components. This dual role makes them promising for complex diseases.

In the future, several challenges still need to be addressed before PELNs can be widely used in clinical practice. First, their therapeutic effects must be reproducible and stable At present, PELNs derived from different plants may show differences in composition and function, and these differences need systematic study. Second, although animal experiments have demonstrated that PELNs can suppress inflammation, reduce oxidative stress, and promote tissue repair, their safety, effective dosage, and long-term benefits in humans remain to be clarified. Furthermore, combining PELNs with existing therapies could further improve outcomes. For example, in cancer therapy, PELNs may serve as natural carriers for nucleic acids and be used in combination with chemotherapy or immune checkpoint inhibitors, which might increase efficacy and reduce side effects.

Looking ahead, PELNs show broad prospects in treatment. They may become not only the next generation of drug delivery platforms, but also independent therapeutic agents. With further progress in preparation methods, mechanistic studies, and clinical validation, PELNs may bring new breakthroughs for the treatment of currently intractable diseases.

Funding

National Natural Science Foundation of China (82405273), Natural Science Foundation of Hubei Province (2022CFD023 and 2024AFD299). Basic scientific research project of the Educational Department of Liaoning Province (JYTMS20230584). Natural Science Foundation of Liaoning Province (2023-MSLH-028).

Disclosure

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

References

1. Zhao B, Lin H, Jiang X. et al. Exosome-like nanoparticles derived from fruits, vegetables, and herbs: innovative strategies of therapeutic and drug delivery. Theranostics. 2024;14(12):4598–4621. doi:10.7150/thno.97096

2. Yang D, Zhang W, Zhang H, et al. Progress, opportunity, and perspective on exosome isolation – efforts for efficient exosome-based theranostics[J]. Theranostics. 2020;10(8):3684–3707. doi:10.7150/thno.41580

3. Wang W, Wang P, Liang Z, et al. Exosome-like nanovesicles derived from Momordica charantia ameliorate delayed t-PA thrombolysis-induced hemorrhagic transformation by inhibiting the ONOO−/HMGB1/MMP-9 pathway. Journal of Functional Foods. 2024;114:106086. doi:10.1016/j.jff.2024.106086

4. Wang X, Xia J, Yang L, et al. Recent progress in exosome research: isolation, characterization and clinical applications[J]. Cancer Genet Ther. 2023;30(8):1051–1065. doi:10.1038/s41417-023-00617-y

5. Li Y, Wang Y, Zhao H, et al. Engineering Strategies of Plant-Derived Exosome-Like Nanovesicles: current Knowledge and Future Perspectives[J]. Int J Nanomed. 2024;19:12793–12815. doi:10.2147/IJN.S496664

6. Visan KS, Lobb RJ, Ham S, et al. Comparative analysis of tangential flow filtration and ultracentrifugation, both combined with subsequent size exclusion chromatography, for the isolation of small extracellular vesicles[J]. J Extracell Vesicles. 2022;11(9):12266. doi:10.1002/jev2.12266

7. Liu Y, Ren C, Zhan R, et al. Exploring the Potential of Plant-Derived Exosome-like Nanovesicle as Functional Food Components for Human Health: a Review[J]. Foods. 2024;13(5):712. doi:10.3390/foods13050712

8. Bai C, Liu J, Zhang X, et al. Research status and challenges of plant-derived exosome-like nanoparticles[J]. Biomed Pharmacother. 2024;174:116543. doi:10.1016/j.biopha.2024.116543

9. Nguyen YNG, Pham CV, Chowdhury R, et al. Development of Blueberry-Derived Extracellular Nanovesicles for Immunomodulatory Therapy[J]. Pharmaceutics. 2023;15(8):2115. doi:10.3390/pharmaceutics15082115

10. Feng W, Teng Y, Zhong Q, et al. Biomimetic Grapefruit-Derived Extracellular Vesicles for Safe and Targeted Delivery of Sodium Thiosulfate against Vascular Calcification[J]. ACS Nano. 2023;17(24):24773–24789. doi:10.1021/acsnano.3c05261

11. Barzin M, Bagheri AM, Ohadi M, et al. Application of plant-derived exosome-like nanoparticles in drug delivery[J]. Pharmaceutical Development Technol. 2023;28(5):383–402. doi:10.1080/10837450.2023.2202242

12. Yi C, Lu L, Li Z, et al. Plant-derived exosome-like nanoparticles for microRNA delivery in cancer treatment. Drug Deliv Transl Res. 2025;15(1):84–101. doi:10.1007/s13346-024-01621-x

13. Tembo KM, Wang X, Bolideei M, et al. Exploring the bioactivity of MicroRNAs Originated from Plant-derived Exosome-like Nanoparticles (PELNs): current perspectives. J Nanobiotechnology. 2025;23(1):563. doi:10.1186/s12951-025-03602-9

14. Xu T, Zhu Y, Lin Z, et al. Evidence of Cross-Kingdom Gene Regulation by Plant MicroRNAs and Possible Reasons for Inconsistencies. J Agric Food Chem. 2024;72(9):4564–4573. doi:10.1021/acs.jafc.3c09097

15. Xu XH, Yuan TJ, Dad HA, et al. Plant Exosomes As Novel Nanoplatforms for MicroRNA Transfer Stimulate Neural Differentiation of Stem Cells In Vitro and In Vivo. Nano Lett. 2021;21(19):8151–8159. doi:10.1021/acs.nanolett.1c02530

16. Kim J, Zhu Y, Chen S, et al. Anti-glioma effect of ginseng-derived exosomes-like nanoparticles by active blood-brain-barrier penetration and tumor microenvironment modulation. J Nanobiotechnology. 2023;21(1):253. doi:10.1186/s12951-023-02006-x

17. Li Z, Wang H, Yin H, Bennett C, Zhang HG, Guo P. Arrowtail RNA for Ligand Display on Ginger Exosome-like Nanovesicles to Systemic Deliver siRNA for Cancer Suppression. Sci Rep. 2018;8(1):14644. doi:10.1038/s41598-018-32953-7

18. Wang D, Mei Z, Zhao T, et al. The roles of plant-derived nanovesicles in malignant tumours: a bibliometric analysis[J]. Int J Biol Macromol. 2025;305(Pt 2):141112. doi:10.1016/j.ijbiomac.2025.141112

19. Cui WW, Ye C, Wang KX, et al. Momordica. charantia-Derived Extracellular Vesicles-Like Nanovesicles Protect Cardiomyocytes Against Radiation Injury via Attenuating DNA Damage and Mitochondria Dysfunction[J]. Front Cardiovascular Med. 2022;9:864188. doi:10.3389/fcvm.2022.864188

20. Yan G, Xiao Q, Zhao J, et al. Brucea javanica derived exosome-like nanovesicles deliver miRNAs for cancer therapy[J]. J Control Release. 2024;367:425–440. doi:10.1016/j.jconrel.2024.01.060

21. Ju S, Mu J, Dokland T, et al. Grape Exosome-like Nanoparticles Induce Intestinal Stem Cells and Protect Mice From DSS-Induced Colitis[J]. Mol Ther. 2013;21(7):1345–1357. doi:10.1038/mt.2013.64

22. Li S, Zhang R, Wang A, et al. Panax notoginseng: derived exosome-like nanoparticles attenuate ischemia reperfusion injury via altering microglia polarization[J]. J Nanobiotechnol. 2023;21(1):416. doi:10.1186/s12951-023-02161-1

23. Zhu Z, Liao L, Gao M, et al. Garlic-derived exosome-like nanovesicles alleviate dextran sulphate sodium-induced mouse colitis via the TLR4/MyD88/NF-κB pathway and gut microbiota modulation. Food Funct. 2023;14(16):7520–7534. doi:10.1039/D3FO01094E

24. Deng Z, Rong Y, Teng Y, et al. Broccoli-Derived Nanoparticle Inhibits Mouse Colitis by Activating Dendritic Cell AMP-Activated Protein Kinase[J]. Mol Ther. 2017;25(7):1641–1654. doi:10.1016/j.ymthe.2017.01.025

25. He C, Wang K, Xia J, et al. Natural exosomes-like nanoparticles in mung bean sprouts possesses anti-diabetic effects via activation of PI3K/Akt/GLUT4/GSK-3β signaling pathway[J]. J Nanobiotechnol. 2023;21(1):349. doi:10.1186/s12951-023-02120-w

26. Kim DK, Rhee WJ. Antioxidative Effects of Carrot-Derived Nanovesicles in Cardiomyoblast and Neuroblastoma Cells[J]. Pharmaceutics. 2021;13(8):1203. doi:10.3390/pharmaceutics13081203

27. Zhuang X, Deng ZB, Mu J, et al. Ginger-derived nanoparticles protect against alcohol-induced liver damage[J]. J Extracell Vesicles. 2015;4(1):28713. doi:10.3402/jev.v4.28713

28. Sundaram K, Teng Y, Mu J, et al. Outer Membrane Vesicles Released from Garlic Exosome-like Nanoparticles (GaELNs) Train Gut Bacteria that Reverses Type 2 Diabetes via the Gut-Brain Axis[J]. Small. 2024;20(20):2308680. doi:10.1002/smll.202308680

29. Raimondo S, Saieva L, Cristaldi M, et al. Label-free quantitative proteomic profiling of colon cancer cells identifies acetyl-CoA carboxylase alpha as antitumor target of Citrus limon-derived nanovesicles[J]. J Proteomics. 2018;173:1–11. doi:10.1016/j.jprot.2017.11.017

30. Liu J, Xiang J, Jin C, et al. Medicinal plant-derived mtDNA via nanovesicles induces the cGAS-STING pathway to remold tumor-associated macrophages for tumor regression[J]. J Nanobiotechnol. 2023;21(1):78. doi:10.1186/s12951-023-01835-0

31. Ou X, Wang H, Tie H, et al. Novel plant-derived exosome-like nanovesicles from Catharanthus roseus: preparation, characterization, and immunostimulatory effect via TNF-α/NF-κB/PU.1 axis[J]. J Nanobiotechnol. 2023;21(1):160. doi:10.1186/s12951-023-01919-x

32. Cao M, Yan H, Han X, et al. Ginseng-derived nanoparticles alter macrophage polarization to inhibit melanoma growth[J]. J ImmunoTherapy Cancer. 2019;7(1):326. doi:10.1186/s40425-019-0817-4

33. Orefice NS, Di Raimo R, Mizzoni D, et al. Purposing plant-derived exosomes-like nanovesicles for drug delivery: patents and literature review[J]. Expert Opin Ther Patents. 2023;33(2):89–100. doi:10.1080/13543776.2023.2195093

34. Sriwastva MK, Deng Z, Wang B, et al. Exosome‐like nanoparticles from Mulberry bark prevent DSS‐induced colitis via the AhR/COPS8 pathway[J]. EMBO Rep. 2022;23(3):e53365. doi:10.15252/embr.202153365

35. Li JH, Xu J, Huang C, et al. Houttuynia cordata-Derived Exosome-Like Nanoparticles Mitigate Colitis in Mice via Inhibition of the NLRP3 Signaling Pathway and Modulation of the Gut Microbiota[J]. Int J Nanomed. 2024;19:13991–14018. doi:10.2147/IJN.S493434

36. Wang F, Yuan M, Shao C, et al. Momordica charantia-Derived Extracellular Vesicles Provide Antioxidant Protection in Ulcerative Colitis[J]. Molecules. 2023;28(17):6182. doi:10.3390/molecules28176182

37. Zhang M, Viennois E, Prasad M, et al. Edible ginger-derived nanoparticles: a novel therapeutic approach for the prevention and treatment of inflammatory bowel disease and colitis-associated cancer[J]. Biomaterials. 2016;101:321–340. doi:10.1016/j.biomaterials.2016.06.018

38. Zhu M, Wang S, Yue N, et al. “One stone three birds”: andrographis paniculata-derived exosome-like nanoparticles mitigate dextran sulfate sodium-induced colitis. Chin Med J. 2025;2025:10–97

39. Gong Q, Sun C, Jiang T, Guo Y. Zanthoxylum bungeanum-Derived Nanobiotics for Effective Against Ulcerative Colitis in Mouse Model. Int J Nanomed. 2025;20:6317–6331. doi:10.2147/IJN.S515961

40. Huang S, Zhang M, Li X, et al. Formulation, characterization, and evaluation of curcumin-loaded ginger-derived nanovesicles for anti-colitis activity[J]. J Pharm Anal. 2024;14(12):101014. doi:10.1016/j.jpha.2024.101014

41. Liu B, Li X, Yu H, et al. Therapeutic potential of garlic chive-derived vesicle-like nanoparticles in NLRP3 inflammasome-mediated inflammatory diseases[J]. Theranostics. 2021;11(19):9311–9330. doi:10.7150/thno.60265

42. Liu B, Lu Y, Chen X, et al. Protective Role of Shiitake Mushroom-Derived Exosome-Like Nanoparticles in D-Galactosamine and Lipopolysaccharide-Induced Acute Liver Injury in Mice[J]. Nutrients. 2020;12(2):477. doi:10.3390/nu12020477

43. Xu F, Mu J, Teng Y, et al. Restoring Oat Nanoparticles Mediated Brain Memory Function of Mice Fed Alcohol by Sorting Inflammatory Dectin-1 Complex Into Microglial Exosomes[J]. Small. 2022;18(6):2105385.

44. Chen X, Liu B, Li X, et al. Identification of anti-inflammatory vesicle-like nanoparticles in honey[J]. J Extracell Vesicles. 2021;10(4):e12069. doi:10.1002/jev2.12069

45. Naselli F, Volpes S, Cardinale S, et al. New Nanovesicles from Prickly Pear Fruit Juice: a Resource with Antioxidant, Anti-Inflammatory, and Nutrigenomic Properties[J]. Cells. 2024;13(21):1756. doi:10.3390/cells13211756

46. Urzì O, Cafora M, Ganji NR, et al. Lemon-derived nanovesicles achieve antioxidant and anti-inflammatory effects activating the AhR/Nrf2 signaling pathway[J]. iScience. 2023;26(7):107041. doi:10.1016/j.isci.2023.107041

47. Perut F, Roncuzzi L, Avnet S, et al. Strawberry-Derived Exosome-Like Nanoparticles Prevent Oxidative Stress in Human Mesenchymal Stromal Cells[J]. Biomolecules. 2021;11(1):87. doi:10.3390/biom11010087

48. Kilasoniya A, Garaeva L, Shtam T, et al. Potential of Plant Exosome Vesicles from Grapefruit (Citrus × paradisi) and Tomato (Solanum lycopersicum) Juices as Functional Ingredients and Targeted Drug Delivery Vehicles[J]. Antioxidants. 2023;12(4):943. doi:10.3390/antiox12040943

49. Kim JS, Eom JY, Kim HW, et al. Hemp sprout-derived exosome-like nanovesicles as hepatoprotective agents attenuate liver fibrosis[J]. Biomater Sci. 2024;12(20):5361–5371. doi:10.1039/D4BM00812J

50. Ma C, Liu K, Wang F, et al. Neutrophil membrane-engineered Panax ginseng root-derived exosomes loaded miRNA 182-5p targets NOX4/Drp-1/NLRP3 signal pathway to alleviate acute lung injury in sepsis: experimental studies[J]. Int J Surg. 2024;110(1):72. doi:10.1097/JS9.0000000000000789

51. Raimondo S, Naselli F, Fontana S, et al. Citrus limon -derived nanovesicles inhibit cancer cell proliferation and suppress CML xenograft growth by inducing TRAIL-mediated cell death[J]. Oncotarget. 2015;6(23):19514–19527. doi:10.18632/oncotarget.4004

52. Yang M, Liu X, Luo Q, et al. An efficient method to isolate lemon derived extracellular vesicles for gastric cancer therapy[J]. J Nanobiotechnol. 2020;18(1):100. doi:10.1186/s12951-020-00656-9

53. Zu M, Xie D, Canup BSB, et al. ‘Green’ nanotherapeutics from tea leaves for orally targeted prevention and alleviation of colon diseases[J]. Biomaterials. 2021;279:121178. doi:10.1016/j.biomaterials.2021.121178

54. Chen Q, Li Q, Liang Y, et al. Natural exosome-like nanovesicles from edible tea flowers suppress metastatic breast cancer via ROS generation and microbiota modulation[J]. Acta Pharmaceutica Sinica B. 2022;12(2):907–923. doi:10.1016/j.apsb.2021.08.016

55. Chen Q, Zu M, Gong H, et al. Tea leaf-derived exosome-like nanotherapeutics retard breast tumor growth by pro-apoptosis and microbiota modulation[J]. J Nanobiotechnol. 2023;21(1):6. doi:10.1186/s12951-022-01755-5

56. Sasaki D, Kusamori K, Takayama Y, et al. Development of nanoparticles derived from corn as mass producible bionanoparticles with anticancer activity[J]. Sci Rep. 2021;11(1):22818. doi:10.1038/s41598-021-02241-y

57. Ma X, Chen N, Zeng P, et al. Hypericum Perforatum-Derived Exosomes-Like Nanovesicles: a Novel Natural Photosensitizer for Effective Tumor Photodynamic Therapy[J]. Int J Nanomed. 2025;20:1529–1541. doi:10.2147/IJN.S510339

58. Stanly C, Alfieri M, Ambrosone A, et al. Grapefruit-Derived Micro and Nanovesicles Show Distinct Metabolome Profiles and Anticancer Activities in the A375 Human Melanoma Cell Line[J]. Cells. 2020;9(12):2722. doi:10.3390/cells9122722

59. Wang B, Guo XJ, Cai H, et al. Momordica charantia-derived extracellular vesicles-like nanovesicles inhibited glioma proliferation, migration, and invasion by regulating the PI3K/AKT signaling pathway[J]. Journal of Functional Foods. 2022;90:104968. doi:10.1016/j.jff.2022.104968

60. Luo X, Zhang X, Xu A, et al. Mechanistic Insights into the Anti-Glioma Effects of Exosome-Like Nanoparticles Derived from Garcinia Mangostana L.: a Metabolomics, Network Pharmacology, and Experimental Study. Int J Nanomed. 2025;20:5407–5427. doi:10.2147/IJN.S514930

61. Chen T, Ma B, Lu S, et al. Cucumber-Derived Nanovesicles Containing Cucurbitacin B for Non-Small Cell Lung Cancer Therapy[J]. Int J Nanomed. 2022;17:3583–3599. doi:10.2147/IJN.S362244

62. Chi Y, Shi L, Lu S, et al. Inhibitory effect of Lonicera japonica-derived exosomal miR2911 on human papilloma virus[J]. J Ethnopharmacol. 2024;318:116969. doi:10.1016/j.jep.2023.116969

63. Cui Z, Liu T, Wen Y, et al. Oral administration of cranberry-derived exosomes attenuates murine premature ovarian failure in association with changes in the specific gut microbiota and diminution in ovarian granulosa cell PANoptosis[J]. Food Funct. 2024;15(23):11697–11714. doi:10.1039/D4FO03468F

64. Qiu FS, Wang JF, Guo MY, et al. Rgl-exomiR-7972, a novel plant exosomal microRNA derived from fresh Rehmanniae Radix, ameliorated lipopolysaccharide-induced acute lung injury and gut dysbiosis[J]. Biomed Pharmacother. 2023;165:115007. doi:10.1016/j.biopha.2023.115007

65. Zou J, Song Q, Shaw PC, et al. Tangerine Peel-Derived Exosome-Like Nanovesicles Alleviate Hepatic Steatosis Induced by Type 2 Diabetes: evidenced by Regulating Lipid Metabolism and Intestinal Microflora[J]. Int J Nanomed. 2024;19:10023–10043. doi:10.2147/IJN.S478589

66. Berger E, Colosetti P, Jalabert A, et al. Use of Nanovesicles from Orange Juice to Reverse Diet-Induced Gut Modifications in Diet-Induced Obese Mice[J]. Mol Ther Methods Clin Dev. 2020;18:880–892. doi:10.1016/j.omtm.2020.08.009

67. Yang S, Lu S, Ren L, et al. Ginseng-derived nanoparticles induce skin cell proliferation and promote wound healing[J]. J Ginseng Res. 2023;47(1):133–143. doi:10.1016/j.jgr.2022.07.005

68. Tan S, Liu Z, Cong M, et al. Dandelion-derived vesicles-laden hydrogel dressings capable of neutralizing Staphylococcus aureus exotoxins for the care of invasive wounds[J]. J Control Release. 2024;368:355–371. doi:10.1016/j.jconrel.2024.02.045

69. Savcı Y, Kırbaş OK, Bozkurt BT, et al. Grapefruit-derived extracellular vesicles as a promising cell-free therapeutic tool for wound healing[J]. Food Funct. 2021;12(11):5144–5156. doi:10.1039/D0FO02953J

70. Şahin F, Koçak P, Güneş MY, et al. In Vitro Wound Healing Activity of Wheat-Derived Nanovesicles[J]. Appl. Biochem. Biotechnol. 2019;188(2):381–394. doi:10.1007/s12010-018-2913-1

71. Abraham AM, Wiemann S, Ambreen G, et al. Cucumber-Derived Exosome-like Vesicles and PlantCrystals for Improved Dermal Drug Delivery[J]. Pharmaceutics. 2022;14(3):476. doi:10.3390/pharmaceutics14030476

72. Trentini M, Zanolla I, Zanotti F, et al. Apple Derived Exosomes Improve Collagen Type I Production and Decrease MMPs during Aging of the Skin through Downregulation of the NF-κB Pathway as Mode of Action[J]. Cells. 2022;11(24):3950. doi:10.3390/cells11243950

73. Cho EG, Choi SY, Kim H, et al. Panax ginseng-Derived Extracellular Vesicles Facilitate Anti-Senescence Effects in Human Skin Cells: an Eco-Friendly and Sustainable Way to Use Ginseng Substances[J]. Cells. 2021;10(3):486. doi:10.3390/cells10030486

74. Sun Z, Zheng Y, Wang T, et al. Aloe Vera Gel and Rind-Derived Nanoparticles Mitigate Skin Photoaging via Activation of Nrf2/ARE Pathway. Int J Nanomed. 2025;20:4051–4067. doi:10.2147/IJN.S510352

75. Lee R, Ko HJ, Kim K, et al. Anti-melanogenic effects of extracellular vesicles derived from plant leaves and stems in mouse melanoma cells and human healthy skin[J]. J Extracell Vesicles. 2020;9(1):1703480. doi:10.1080/20013078.2019.1703480

76. Sundaram K, Mu J, Kumar A, et al. Garlic exosome-like nanoparticles reverse high-fat diet induced obesity via the gut/brain axis[J]. Theranostics. 2022;12(3):1220–1246. doi:10.7150/thno.65427

77. Zhang Y, Zhang X, Kai T, et al. Lycium ruthenicum Murray derived exosome-like nanovesicles inhibit Aβ-induced apoptosis in PC12 cells via MAPK and PI3K/AKT signaling pathways[J]. Int J Biol Macromol. 2024;277:134309. doi:10.1016/j.ijbiomac.2024.134309

78. Cai H, Huang LY, Hong R, et al. Momordica charantia Exosome-Like Nanoparticles Exert Neuroprotective Effects Against Ischemic Brain Injury via Inhibiting Matrix Metalloproteinase 9 and Activating the AKT/GSK3β Signaling Pathway[J]. Front Pharmacol. 2022;13:908830. doi:10.3389/fphar.2022.908830

79. Ye C, Yan C, Bian SJ, et al. Momordica charantia L.-derived exosome-like nanovesicles stabilize p62 expression to ameliorate doxorubicin cardiotoxicity[J]. J Nanobiotechnol. 2024;22(1):464. doi:10.1186/s12951-024-02705-z

80. Zhou HH, Zhou X, Pei J, et al. A fibrin gel-loaded Gouqi-derived nanovesicle (GqDNV) repairs the heart after myocardial infarction by inhibiting p38 MAPK/NF-κB p65 pathway. J Nanobiotechnology. 2025;23(1):535.

81. Shen H, Zhang M, Liu D, et al. Solanum lycopersicum derived exosome-like nanovesicles alleviate restenosis after vascular injury through the Keap1/Nrf2 pathway[J]. Food Funct. 2025;16(2):539–553. doi:10.1039/D4FO03993A

82. Cao Y, Tan X, Shen J, et al. Morinda Officinalis-derived extracellular vesicle-like particles: anti-osteoporosis effect by regulating MAPK signaling pathway[J]. Phytomedicine. 2024;129:155628. doi:10.1016/j.phymed.2024.155628

83. Seo K, Yoo JH, Kim J, et al. Ginseng-derived exosome-like nanovesicles extracted by sucrose gradient ultracentrifugation to inhibit osteoclast differentiation[J]. Nanoscale. 2023;15(12):5798–5808. doi:10.1039/D2NR07018A

84. Hwang JH, Park YS, Kim HS, et al. Yam-derived exosome-like nanovesicles stimulate osteoblast formation and prevent osteoporosis in mice[J]. J Control Release. 2023;355:184–198. doi:10.1016/j.jconrel.2023.01.071

85. Zhou X, Xu S, Zhang Z, et al. Gouqi-derived nanovesicles (GqDNVs) inhibited dexamethasone-induced muscle atrophy associating with AMPK/SIRT1/PGC1α signaling pathway[J]. J Nanobiotechnol. 2024;22(1):276. doi:10.1186/s12951-024-02563-9

86. Del Pozo-Acebo L, López de Las Hazas MC, Tomé-Carneiro J, et al. Therapeutic potential of broccoli-derived extracellular vesicles as nanocarriers of exogenous miRNAs[J]. Pharmacol Res. 2022;185:106472. doi:10.1016/j.phrs.2022.106472

87. Wang B, Zhuang X, Deng ZB, et al. Targeted Drug Delivery to Intestinal Macrophages by Bioactive Nanovesicles Released from Grapefruit[J]. Mol Ther. 2014;22(3):522–534. doi:10.1038/mt.2013.190

88. Wang Q, Zhuang X, Mu J, et al. Delivery of therapeutic agents by nanoparticles made of grapefruit-derived lipids[J]. Nat Commun. 2013;4(1):1867. doi:10.1038/ncomms2886

89. Zhang M, Xiao B, Wang H, et al. Edible Ginger-derived Nano-lipids Loaded with Doxorubicin as a Novel Drug-delivery Approach for Colon Cancer Therapy[J]. Mol Ther. 2016;24(10):1783–1796. doi:10.1038/mt.2016.159

90. You JY, Kang SJ, Rhee WJ. Isolation of cabbage exosome-like nanovesicles and investigation of their biological activities in human cells[J]. Bioact Mater. 2021;6(12):4321–4332. doi:10.1016/j.bioactmat.2021.04.023

91. Xiao Q, Zhao W, Wu C, et al. Lemon-Derived Extracellular Vesicles Nanodrugs Enable to Efficiently Overcome Cancer Multidrug Resistance by Endocytosis-Triggered Energy Dissipation and Energy Production Reduction[J]. Adv Sci. 2022;9(20):2105274. doi:10.1002/advs.202105274

92. Pomatto MAC, Gai C, Negro F, et al. Plant-Derived Extracellular Vesicles as a Delivery Platform for RNA-Based Vaccine: feasibility Study of an Oral and Intranasal SARS-CoV-2 Vaccine[J]. Pharmaceutics. 2023;15(3):974. doi:10.3390/pharmaceutics15030974

93. Mammadova R, Maggio S, Fiume I, et al. Protein Biocargo and Anti-Inflammatory Effect of Tomato Fruit-Derived Nanovesicles Separated by Density Gradient Ultracentrifugation and Loaded with Curcumin[J]. Pharmaceutics. 2023;15(2):333. doi:10.3390/pharmaceutics15020333

94. Wang Q, Ren Y, Mu J, et al. Grapefruit-Derived Nanovectors Use an Activated Leukocyte Trafficking Pathway to Deliver Therapeutic Agents to Inflammatory Tumor Sites[J]. Cancer Res. 2015;75(12):2520–2529. doi:10.1158/0008-5472.CAN-14-3095

95. Liu H, Song J, Zhou L, et al. Construction of curcumin-fortified juices using their self-derived extracellular vesicles as natural delivery systems: grape, tomato, and Orange juices[J]. Food Funct. 2023;14(20):9364–9376. doi:10.1039/D3FO02605A

96. Kim J, Gao C, Guo P, et al. A novel approach to alleviate Acetaminophen-induced hepatotoxicity with hybrid balloon flower root-derived exosome-like nanoparticles (BDEs) with silymarin via inhibition of hepatocyte MAPK pathway and apoptosis[J]. Cell Commun Signaling. 2024;22(1):334. doi:10.1186/s12964-024-01700-z

97. Sarwareddy KK, Divyash A, Sreekanth P, et al. Harnessing tomato-derived small extracellular vesicles as drug delivery system for cancer therapy[J]. Future Science OA. 2025;11(1):2461956. doi:10.1080/20565623.2025.2461956

98. Jiang D, Li Z, Liu H, et al. Plant exosome-like nanovesicles derived from sesame leaves as carriers for luteolin delivery: molecular docking, stability and bioactivity[J]. Food Chem. 2024;438:137963. doi:10.1016/j.foodchem.2023.137963

99. Ishida T, Kawada K, Jobu K, et al. Exosome-like nanoparticles derived from Allium tuberosum prevent neuroinflammation in microglia-like cells[J]. J Pharm Pharmacol. 2023;75(10):1322–1331. doi:10.1093/jpp/rgad062

100. Mao Y, Han M, Chen C, et al. A biomimetic nanocomposite made of a ginger-derived exosome and an inorganic framework for high-performance delivery of oral antibodies[J]. Nanoscale. 2021;13(47):20157–20169. doi:10.1039/D1NR06015E

101. Fang Z, Song M, Lai K, et al. Kiwi-derived extracellular vesicles for oral delivery of sorafenib[J]. Eur J Pharm Sci. 2023;191:106604. doi:10.1016/j.ejps.2023.106604

102. Sharma S, Mahanty M, Rahaman SG, et al. Avocado-derived extracellular vesicles loaded with ginkgetin and berberine prevent inflammation and macrophage foam cell formation[J]. J Cell & Mol Med. 2024;28(7):e18177. doi:10.1111/jcmm.18177

103. Li D, Yi G, Cao G, et al. Dual-Carriers of Tartary Buckwheat-Derived Exosome-Like Nanovesicles Synergistically Regulate Glucose Metabolism in the Intestine-Liver Axis[J]. Small. 2025;21:2410124.

104. Mu J, Zhuang X, Wang Q, et al. Interspecies communication between plant and mouse gut host cells through edible plant derived exosome-like nanoparticles[J]. Mol Nutr Food Res. 2014;58(7):1561–1573. doi:10.1002/mnfr.201300729

105. Chen X, Zhou Y, Yu J. Exosome-like Nanoparticles from Ginger Rhizomes Inhibited NLRP3 Inflammasome Activation[J]. Mol Pharmaceut. 2019;16(6):2690–2699. doi:10.1021/acs.molpharmaceut.9b00246

106. Gasparro R, Gambino G, Duca G, et al. Protective effects of lemon nanovesicles: evidence of the Nrf2/HO-1 pathway contribution from in vitro hepatocytes and in vivo high-fat diet-fed rats. Biomed Pharmacother. 2024;180:117532. doi:10.1016/j.biopha.2024.117532

Specialty

Please chooseI’m not a medical professional.Allergy and ImmunologyAnatomyAnesthesiologyBiostatisticsCardiac/Thoracic/Vascular SurgeryCardiologyCritical CareDentistryDermatologyDiabetes and EndocrinologyEmergency MedicineEpidemiology and Public HealthFamily MedicineForensic MedicineGastroenterologyGeneral PracticeGeneticsGeriatricsHealth PolicyHematologyHIV/AIDSHospital-based MedicineI’m not a medical professional.Infectious DiseaseIntegrative/Complementary MedicineInternal MedicineInternal Medicine-PediatricsMedical Education and SimulationMedical PhysicsMedical StudentNephrologyNeurological SurgeryNeurologyNuclear MedicineNutritionObstetrics and GynecologyOccupational HealthOncologyOphthalmologyOptometryOral MedicineOrthopaedicsOsteopathic MedicineOtolaryngologyPain ManagementPalliative CarePathologyPediatricsPediatric SurgeryPharmacologyPhysical Medicine and RehabilitationPlastic SurgeryPodiatryPreventive MedicinePsychiatryPsychologyPulmonologyRadiation OncologyRadiologyRheumatologySubstance Use and AddictionSurgeryTherapeuticsTraumaUrologyMiscellaneous

Introduction

Depression is a prevalent clinical mental illness characterized by a persistent low mood accompanied by varying degrees of cognitive and behavioral changes, often resulting in functional impairment. It can affect a patient’s education, work, and social life, and in severe cases, may lead to suicide.¹ A Chinese mental health survey reported a lifetime prevalence of depression disorder in China of 6.8%, with 53.1% of patients experiencing suicidal ideation, and 15% ultimately dying by suicide.^2–4 Suicide attempts pose a significant threat to patients’ safety and impose a profound psychological and economic burden on families.

Assessment scales are among the most effective tools for evaluating the severity of depression in patients. The Hamilton Depression Scale (HAMD-24) is one of the most widely used tools for depression screening. It helps assess the severity of depression and evaluate treatment effects. It also includes items indicative of suicidal ideation, such as feelings of guilt, despair, and hopelessness. Recent studies suggest that these factors are strongly correlated with suicide risk in patients with depression. Despair, in particular, is identified as a significant predictor, reflecting a core feature of depression that contributes to the development of suicidal thoughts. The HAMD-24’s role in early suicide risk assessment is critical, as it can help identify individuals who may benefit from timely intervention.^5,6

Building on recent ambivalence-focused research,^7,8 there is growing consensus that suicidal desire fluctuates dynamically. Ecological momentary assessment and digital phenotyping now capture real-time swings between the wish to live and the wish to die. Integrating such ambivalence markers with conventional scales like the HAMD-24 could therefore enhance early detection beyond static symptom snapshots.

However, emerging research highlights the ambivalent nature of suicidal ideation—where patients simultaneously experience desire for death and connection to life.⁷ This complexity underscores limitations of static assessments like the HAMD-24. Novel approaches capturing dynamic triggers (eg, real-time affective shifts) may enhance early detection.⁸ Recent computational psychiatry studies advocate integrating passive digital phenotyping (eg, speech patterns, actigraphy) with clinical scales to detect subtle risk signatures preceding crises.^9–12

In fact, most suicides are preventable, particularly by analyzing the factors strongly associated with suicidal ideation on depression scales like the HAMD-24.¹³ This analysis is valuable for the early prevention and intervention of suicidal behaviors. Such insights can serve as a theoretical reference for developing new scales focused on depression and suicide risk assessment.^14–16

Machine learning is a subset of artificial intelligence that selects the optimal algorithm from complex datasets, effectively addressing the limitations of traditional statistical methods.¹⁷ It can automatically prioritize variables based on relevance, incorporate them into the most efficient model, and identify and manage nonlinear relationships and interactions between variables.¹⁸ Walsh et al found that machine learning models predicted suicide risk more accurately than traditional logistic regression analysis methods using databases, with random forest (RF) and support vector machine (SVM) algorithms demonstrating the highest accuracy.^19–22

In recent years, machine learning has been widely applied to population-based suicide predictions, yet critical gaps remain in applying these techniques specifically to clinical depression scales for suicidal ideation prediction. The existing research combining machine learning with depression scales has the following issues:^23–25 1. Lack of comparative analysis of diverse algorithms, potentially overlooking optimal model performance; 2. There is limited exploration of the relative importance and interactions of characteristic symptoms in mature clinical assessment scales such as HAMD-24, which hinders clinical interpretability and the identification of core mechanistic pathways; 3. The main focus is on population level risks, lacking granular symptom profiles for validated clinical evaluations and failing to leverage the rich, standardized symptom data inherent in widely used scales like the HAMD-24 for individualized risk prediction within clinical workflows. Subsequently, it employs and rigorously compares four distinct machine learning algorithms selected for their complementary strengths in clinical prediction tasks: an SVM model (effective in high-dimensional spaces and robust to outliers),²⁶ a naive Bayes classification (NBC) model (computationally efficient and well suited for probabilistic inference),²⁷ an RF model (excellent handling of complex interactions and feature importance estimation),²⁸ and an extremely random tree classification (ERTC) model (enhances diversity and robustness through extreme randomization, potentially reducing overfitting).²⁹ The classification and prediction performances of these four models were compared, and the most predictive model was selected to analyze factors associated with suicidal ideation. This dual approach aims to both characterize associated factors and enable early interventions and reduce the occurrence of suicidal behavior while providing transparent insights into key predictive features within the HAMD-24. Prior machine learning studies have relied on heterogeneous data sources (EHRs, social media) rather than standardized clinical scales, limiting bedside utility. Moreover, no study has systematically compared SVM, NBC, RF, and ERTC on HAMD-24 items while excluding the direct suicide item to avoid circularity.

Based on the previous research results, we have put forward the following hypotheses:

Hypothesis 1: An ensemble tree model (ERTC) will outperform SVM, NBC, and RF in predicting suicidal ideation (AUC difference ≥ 0.05).

Hypothesis 2: Among HAMD-24 items (excluding Item 3), despair, guilt, inferiority, work and interests, depressive emotions may be server as the five strongest predictors (top quartile of feature importance).

Population and Sample

Inclusion and Exclusion Criteria

A total of 374 patients diagnosed with depression were involved in this study, who received treatment at the psychological clinic of the Changzhou Second People’s Hospital between March 2022 and October 2023, via consecutive sampling of all eligible out-patients during the study window. A priori power analysis was conducted using G*Power 3.1. Based on an expected medium effect size (Cohen’s f² = 0.15), α = 0.05, power (1-β) = 0.80, and 23 predictor variables (demographics + HAMD-24 items excluding Item 3), the minimum required sample size was 190. Our final sample (N = 374) exceeds this threshold by >95%, ensuring robust statistical power for both traditional analyses and machine learning modeling. This sample size also adheres to the heuristic of ≥10 events per predictor variable (EPV) for regression-based models (23 predictors × 10 = 230; our suicidal ideation group had 233 cases) and meets computational requirements for complex ensemble algorithms like ERTC.^28,29

The inclusion criteria were as follows: ① Fulfillment of the diagnostic criteria for depression as outlined in the fifth edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5), confirmed by two psychiatrists at the attending level or higher;³⁰ ② No gender restrictions, with ages ranging from 18 to 60 years; ③ HAMD-24 scores of ≥8 points; ④ Ability to understand the questionnaire and cooperate with its completion; ⑤ Obtaining informed consent from the patient or their legal guardian. The exclusion criteria were as follows: ① Coexisting schizophrenia, mania, bipolar disorder, or other mental illnesses; ② Other neurological or severe physical conditions; ③ Secondary depression caused by other medical conditions.

To minimize confounding effects:

Antidepressant use (type/dose) was recorded and included as a covariate in statistical analyses;

Demographic variables (age, gender, education) showing group differences (Factors Associated with Suicidal Ideation: DemoFigureic Characteristics) were controlled via multivariate regression;

Stratified sampling preserved class balance (suicidal ideation yes/no) during data splitting for machine learning.

Demographic covariates (age, gender, education) and antidepressant status were entered as covariates in the ERTC model to control residual confounding.

This study received approval from the Medical Ethics Committee of Changzhou Second People’s Hospital (Approval No.: 2020KY04-01). All patients were informed about the research objectives and provided written informed consent. Data anonymization was implemented by assigning unique identifiers, and access was restricted to the research team.

Data Collection

Instrumentation

This study employed a self-designed questionnaire to gather general information, including age, gender, years of education, smoking and drinking history, and antidepressant use. Antidepressant use: Currently prescribed medication for ≥4 weeks at time of assessment. Smoking/drinking history: Regular use (≥3 times/week) for >6 months.

Scale Evaluation

The HAMD-24 is a widely used scale for assessing depression clinically, consisting of 24 items and 7 factors (anxiety/somatization, weight, cognitive impairment, day/night changes, delays, sleep disorders, and feelings of despair). The total score indicates the severity of depression, with higher scores indicating more severe depression. This scale demonstrates strong reliability and validity, with coefficients of 0.99 and 0.37, respectively.⁶ In this study, the scale was used to assess depression severity, with a score of less than 8 points indicating no depressive symptoms, less than 20 points indicating mild symptoms, 20 to 35 points indicating moderate symptoms, and above 35 points indicating severe symptoms. Item 3 of the HAMD-24 assesses suicide risk, and to avoid interference with this item, previous studies have typically excluded it when investigating the correlation between suicide risk and depressive symptom severity.³¹ Therefore, this study excluded item 3 in assessing the correlation between HAMD-24 factors and suicide risk. The BSI-CV consists of 19 items, each scored on a scale of 0 to 2. Items 1 to 5 assess suicidal ideation, while items 6 to 19 evaluate suicidal tendencies. If the answers to items 4 and 5 are “none”, the patient is considered not to have suicidal ideation and does not need to complete the remaining items. If the answers to items 4 or 5 are “weak” or “moderate to strong”, the patient is considered to have suicidal ideation and must complete the remaining items. The total score on the BSI-CV ranges from 0 to 38 points, with higher scores indicating stronger suicidal ideation and a higher suicide risk. This study used only the first 5 items of the BSI-CV to evaluate suicidal ideation. The scale’s Cronbach α coefficient was 0.78.³²

Model Framework

The machine learning prediction model involved several steps:

Data preprocessing: Exclusion of HAMD-24 Item 3 (suicide item) to avoid target leakage;

Train-test split: Random stratified partitioning (80% training, 20% testing) to maintain class distribution;

Model development: Implementation of SVM, NBC, RF, and ERTC using scikit-learn (v1.2.2);

Hyperparameter tuning: 5-fold cross-validation on training set with randomized search (100 iterations);

Model validation: Evaluation on held-out test set;

Final evaluation: Performance metrics calculation.

The flowchart of the machine learning prediction model is shown in Figure 1.

Figure 1 Flow chart of machine learning prediction model.

Key parameters:

Cross-validation: 5 folds with stratified sampling; Tree-based models (RF/ERTC): nestimators=200, maxdepth=10 (optimized via cross-validation); SVM: RBF kernel, C=1.0, gamma=“scale”; NBC: Gaussian priors.

After comprehensive evaluation, the ERTC model demonstrated superior prediction performance.

Sampling Rationale for Machine Learning: The dataset was randomly split into training (80%, n=299) and testing (20%, n=75) sets using stratified sampling to preserve the distribution of the target variable (suicidal ideation). This partitioning ratio optimizes model training while retaining sufficient independent samples for unbiased validation, aligning with best practices in clinical machine learning.^17,19

Reproducibility: Random seed 42 was fixed throughout all randomized procedures (data splitting, model initialization). Complete code and preprocessing scripts are available from corresponding author upon request.

Statistical Methods

Statistical analysis was conducted using the SPSS 25.0 software. Continuous data were assessed for normality using Shapiro–Wilk tests. Non-normally distributed clinical data are expressed as medians (M) with interquartile ranges (P25, P75). Non-parametric rank sum tests (Mann–Whitney U-tests) were applied to two independent samples, and rank sum tests were used for comparisons between groups. Comparisons of count data were conducted using chi-squared (χ²) tests or Fisher’s exact test where cell counts were <5, with results presented as cases (%). A Bonferroni correction was applied for multiple comparisons of HAMD-24 items (adjusted P < 0.0022 (0.05/23 items)). Statistical significance was determined at a threshold of P <0.05. Non-parametric tests were selected because (i) age and HAMD-24 items were non-normally distributed (Shapiro–Wilk p < 0.001) and (ii) ordinal or binary variables precluded parametric alternatives. These tests served only to guide feature inclusion, not to test causal hypotheses.

Machine learning models were implemented in Python 3.9 using scikit-learn (v1.2.2). All models underwent identical preprocessing and evaluation protocols to ensure fair comparison. The SVM method, designed based on optimization strategies, minimizes influence from outliers and demonstrates strong generalization ability to achieve global optimal solutions.²⁶ NBC is a well-established probabilistic algorithm used for text classification, providing efficient, stable classification, rapid computation, and high accuracy.²⁷ RF is an ensemble learning algorithm based on decision trees, capable of balancing classification errors and maintaining prediction performance, with faster learning and training efficiency.²⁸ ERTC is an ensemble learning technique that constructs multiple decision trees using the Gini index for data splitting and aggregates different results to output classification outcomes.²⁹

Model performance was assessed using metrics including accuracy, precision, recall, F1-scores, Kappa coefficients, Matthews correlation coefficient (MCC), and area under the curve (AUC) values. The optimal model was selected based on these performance indicators.

Results

Factors Associated with Suicidal Ideation: Demographic Characteristics

To provide clinicians with baseline information on potential confounders, we first conducted exploratory group comparisons; these analyses were not intended to predict suicidal ideation but to inform feature selection for the machine-learning pipeline.

This study included a total of 374 patients, who were divided into two groups: 141 without suicidal ideation and 233 with suicidal ideation. As demonstrated in Table 1, no statistically significant differences were observed between the two groups in terms of the first/follow-up visit (χ² = 1.15, P = 0.28), gender (χ² = 1.98, P = 0.16), educational level (χ² = 6.27, P = 0.099), smoking history (χ² = 1.18, P = 0.277), and drinking history (χ² = 2.66, P = 0.103). However, the median age of those with suicidal ideation was significantly lower than that of those without (Z = −6.62, P < 0.001), and a statistically significant difference was found in the use of antidepressants (χ² = 4.21, P < 0.05). These variables were subsequently included as covariates in machine learning feature engineering to mitigate confounding.

Table 1 General Information of Depressed Patients with and without Suicidal Ideation

Factors Associated with Suicidal Ideation: HAMD-24 Symptom Profiles

Statistically significant differences (Table 2) were identified for the HAMD-24 total score and 17 sub-domains: depression emotions (Z = −6.28., P < 0.001), guilt (Z = −5.67, P < 0.001), difficulty falling asleep (Z = −3.83, P < 0.001), work and interests (Z = −7.07, P < 0.001), psychomotor retardation (Z = −2.17, P < 0.05), agitation (Z = −2.06, P < 0.05), somatic anxiety (Z = −3.48, P < 0.001), gastrointestinal symptoms (Z = −4.05, P < 0.001), systemic symptoms (Z = −3.82, P < 0.001), hypochondriasis (Z = −2.01, P < 0.05), weight loss (Z = −3.73, P < 0.001), self-awareness (Z = −3.15, P < 0.05), diurnal variation (Z = −3.53, P < 0.001), paranoid symptoms (Z = −5.79, P < 0.001), reduced abilities (Z = −3.49, P < 0.001), despair (Z = −8.01, P < 0.001), and inferiority complex (Z = −6.49, P < 0.001). The remaining 6 sub-domains—lack of deep sleep (Z = −0.38, P = 0.707), early awakening (Z = −1.78, P = 0.075), psychological anxiety (Z = −1.50, P = 0.134), sexual symptoms (Z = −1.47, P = 0.141), personality disintegration or reality disintegration (Z = −1.43, P = 0.152), and compulsive symptoms (Z = −1.53, P = 0.127)—showed no significant differences. The negative z-value indicates that the depression score among individuals without suicidal ideation is lower than among those with suicidal ideation. The total HAMD-24 score (excluding item 3) was significantly higher in the suicidal ideation group (Z = −8.81, P < 0.001).

Table 2 Comparison of HAMD-24 Total Scores Between Depressed Patients with and without Suicidal Ideation [M (P25, P75)]

Analysis of Machine Learning Results

Accuracy refers to the proportion of correctly classified samples in relation to the total number of samples in a given class. The AUC is an evaluation metric that assesses the quality of a binary classification model, indicating the probability that the predicted value of a positive example exceeds that of a negative example. The recall rate, (true examples (TP)/(TP + false negative examples (FN))), represents the ratio of correctly predicted positive samples to the total number of actual positive samples.

Precision, (TP/(TP + false positive examples (FP)), represents the ratio of correctly predicted positive samples to the total number of predicted positive samples. The F1 score is defined as F1 = 2/(1/recall + 1/precision).

The Kappa coefficient is a consistency measure used to assess the effectiveness of classifications, specifically to determine whether the model’s predicted results align with the actual classification outcomes. A value greater than 0.5 indicates strong classification performance.

The MCC coefficient is used to evaluate the performance of binary classification models, especially when dealing with imbalanced datasets. It incorporates TP, TN, FP, and FN, offering a single value that summarizes classification quality, with values greater than 0.5 indicating strong classification performance.

As demonstrated in Table 3, the performance evaluation of the four machine learning models revealed that the ERTC model achieved excellent classification performance, with a prediction accuracy of 77.75% on the independent test set. Additional indicators demonstrated that this model exhibited strong classification performance in analyzing suicidal ideation.

Table 3 Prediction Results of Four Machine Learning Algorithm Models

The area under the receiver operating characteristic (ROC) curve, known as the AUC, serves as an indicator for evaluating classifier performance. A larger AUC reflects a better classifier performance. An AUC greater than 0.9 is considered very good, 0.8 to 0.9 is good, 0.7 to 0.79 is median, and less than 0.7 is poor. The closer the ROC curve is to the upper left corner, the better the classification performance of the algorithm. Based on the ROC curves and AUC values shown in Figure 2, the ERTC model demonstrated high classification performance in predicting suicidal ideation.

Figure 2 ROC Curves for ExtraTreesClassifier.

Based on the confusion matrix presented in Figure 3, the ERTC model demonstrated good classification accuracy, achieving a correct classification rate of 77%.

Figure 3 ExtraTreesClassifier Confusion Matrix.

Notably, this represents the first machine learning study to identify symptom-level predictors of suicidal ideation exclusively from HAMD-24 items (excluding Item 3) with clinically actionable accuracy (AUC=0.80). The ERTC model’s superior performance—outperforming established algorithms like SVM and RF—validates its utility for precision psychiatry applications.

The feature analysis of the ERTC model, demonstrated in Figure 4, identified the most important features as feelings of despair, guilt, inferiority, work and interest, and depression.

Figure 4 Feature Importance Plot.

Discussion

Unlike prior studies that combined heterogeneous clinical notes or social-media data,^19,25 our study uniquely isolates symptom-level predictors within a single, widely adopted scale (HAMD-24) and demonstrates that ensemble tree methods outperform SVM and RF under these constraints.

This study pioneers the integration of machine learning with granular HAMD-24 symptom profiling to predict suicidal ideation in depression, addressing a critical gap in translating population-level suicide risk models into clinically actionable tools. While numerous studies have confirmed associations between depression severity and suicidality,^4,33,34 and others have applied machine learning to suicide prediction using diverse data sources (eg, electronic health records, social media, multi-omics data),^16,17,19,25 our work specifically addresses the under-explored potential of leveraging “routine clinical scale data (HAMD-24)” for early suicide ideation detection within a standardized diagnostic framework.

Hypothesis 1: Model Performance

Our work bridges this gap through three key advances: First, by employing an ensemble-based Extremely Randomized Trees Classifier (ERTC), we not only confirmed known associations but also quantified the hierarchical symptom contributions (despair > guilt > inferiority > work/interest > depression) to suicidal ideation with unprecedented precision, providing symptom-level weights rarely captured in traditional analyses or population-level machine learning models. Second, we achieved clinically statistically significant prediction accuracy (AUC=0.80) using only routine HAMD-24 items—excluding the direct suicide query (Item 3) to avoid tautology—thereby demonstrating the scale’s latent capacity for risk stratification beyond its original design and distinct from studies relying on explicit suicide items or non-scale data. This approach mitigates response bias inherent in direct suicide questioning. Third, we demonstrated ERTC’s superior robustness over established algorithms (SVM, RF) in handling psychiatric symptom data,^16,21 attributable to its extreme random subspace sampling and node splitting, which mitigates overfitting and captures complex feature interactions inherent in depression psychopathology. This finding contrasts with studies where SVM or RF often performed best,^25,27 suggesting ERTC’s particular suitability for modeling complex symptom interactions within constrained scale data. This methodological synergy not only advances mechanistic understanding of suicide risk but delivers a scalable framework for real-world clinical decision support rooted in existing assessment practices.

Demographic patterns reinforced known epidemiological trends while underscoring clinical nuances. The heightened vulnerability of younger patients aligns with developmental psychopathology models positing that impulsivity, identity instability, and maladaptive coping peak in early adulthood, amplifying suicide risk when comorbid with depression.³⁵ The significant reduction in suicidal ideation among antidepressant users highlighted treatment’s protective role, potentially mediated by neurotransmitter modulation (eg, enhanced serotonin signaling reducing impulsivity) or psychological mechanisms (eg, restored agency).³⁶ This reinforces guidelines advocating prompt pharmacotherapy initiation in moderate-to-severe depression. Furthermore, a higher total HAMD-24 score (excluding item 3) was strongly associated with an increased likelihood of suicidal ideation, corroborating previous research linking the severity of depressive symptoms to suicide risk.³³

Hypothesis 2: Key Symptom Predictors

Consistent with Beck’s hopelessness theory, despair—conceptualised as negative future expectancy—was the single strongest predictor in our model (feature importance = 0.27), corroborating meta-analytic evidence that hopelessness accounts for 76% of the explained variance in suicidal ideation.^34,37 Theoretical frameworks position despair: conceptualized as a future-oriented cognitive schema characterized by negative expectations (“nothing will improve”) and perceived inescapability (“no way out”)³⁷—as an essential proximal cause of suicidal thoughts.^38–41 Notably, contemporary models integrate ambivalence—recognizing suicidal urgency often coexists with “countervailing motivations” (eg, fear of death, responsibility to family). This may explain why despair alone is insufficient to predict attempts; our model could be augmented by ambivalence metrics. Neurocognitively, this may reflect dysfunction in prefrontal cortical circuits responsible for future prospection and problem-solving, trapping individuals in a cycle of hopelessness. Our findings solidify despair’s critical role within the HAMD-24 framework, while also underscoring the clinical necessity of addressing closely ranked co-factors (guilt, inferiority), given the marginal quantitative difference in their importance scores. Mechanistically, despair may propagate suicidal ideation through two synergistic pathways: 1. Direct pathway: By inducing cognitive constriction—a narrowing of perceived options—where suicide is misappraised as the sole viable solution to unbearable psychological pain;^38,42 2. Indirect pathway: By eroding psychological resilience—the capacity to adaptively cope with adversity—through diminished self-efficacy, impaired access to positive memories, and reduced motivation to seek support, thereby disabling protective mechanisms.^43–45 This dual-pathway model underscores despair’s pernicious role in both motivating suicidal escape and disabling natural buffers against it.

The secondary prominence of guilt and inferiority complex the interpersonal dimension of suicide risk. Guilt—operationalized as “burdening guilt” involving irrational self-condemnation and perceived liability to others⁴⁶ and inferiority—rooted in chronic low self-worth and social comparison.⁴⁷ Align precisely with Joiner’s Interpersonal Theory of Suicide (IPTS).⁴⁰ IPTS posits that suicidal desire emerges from co-occurring “thwarted belongingness” (social alienation) and “perceived burdensomeness” (self-hate as a liability). Our findings validate this model within the HAMD-24 architecture: guilt embodies burdensomeness (“I am a drain on my family”), while inferiority fuels belongingness deficits (“I am unworthy of connection”). These factors likely contribute to suicidal ideation by fostering cognitive distortions, social isolation, and reinforcing feelings of hopelessness and worthlessness.^39,48 Notably, guilt’s strong predictive power persists despite potential scale-limited assessment in HAMD-24 versus BDI, where it exhibits denser symptom-network connectivity.⁴⁹ This suggests that guilt’s clinical relevance may be underestimated in HAMD-centric evaluations, warranting supplemental assessment when risk is elevated.

Work and interests loss and depressive emotions, though lower-ranked, reveal cyclical psychobehavioral mechanisms. Anhedonia-driven social withdrawal initiates a self-perpetuating cascade:^49,50 Isolation → eroded social support → exacerbated despair guilt → deeper depression → reinforced withdrawal. This “depression-withdrawal feedback loop” is neurobiologically scaffolded by reward system dysfunction (eg, ventral striatal hypoactivity), diminishing motivation for social engagement.⁵¹ Critically, withdrawal’s predictive value extends beyond functional impairment; it signifies disengagement from protective social anchors, depriving patients of reality testing, emotional scaffolding, and reasons for living.^52,53 Meanwhile, pervasive depressive mood—while a foundational symptom—may operate partly via its amplification effect on despair and guilt, illustrating how core affective and cognitive symptoms interact multiplicatively to elevate risk.⁵⁴

Clinical and Research Implications

Our ERTC model converts the standard administration process of the HAMD-24 scale into a dynamic risk-stratification tool. Clinicians can prioritize symptom remediation hierarchically (eg, targeting despair via cognitive restructuring before inferiority via social skills training). The quantified feature weights further guide scale refinement: Future depression-suicide risk instruments could amplify item weighting for despair/guilt or add nuanced guilt descriptors (eg, “feelings of being an unforgivable burden”). Methodologically, ERTC’s success advocates for algorithmic pluralism in psychiatric machine learning—avoiding overreliance on single models (eg, SVM-dominated literature) and leveraging ensemble methods for complex symptom interactions. In clinical work. In clinical practice applications, for early detection, we recommend complementing scale-based screening with: 1. Ecological Momentary Assessment (EMA) to capture real-time symptom fluctuations linked to triggers;^55,56 2. Natural language processing of clinical notes to identify linguistic markers of ambivalence (eg, coexisting hopelessness and future planning);^9,10 3.Actigraphy monitoring to detect behavioral correlates (eg, social withdrawal spikes).^57,58

Limitations and Future Directions

While impactful, our study has constraints: Single-center sampling limits generalizability; antidepressant type/dose was recorded but not standardized across participants, potentially confounding medication effects; the sample size, though sufficient for model development, warrants validation in larger cohorts; modest specificity risks false positives, necessitating secondary screening; and exclusive reliance on HAMD-24 omits biomarkers (eg, inflammatory markers, fMRI connectivity). Future work should: 1. Validate the model in multicentric, culturally diverse cohorts; 2. Incorporate ambivalence measures (eg, Death/Suicide Implicit Association Test) and multimodal digital phenotyping 3. Track temporal symptom dynamics to capture risk flux; 4. Improve specificity via hybrid models (eg, ERTC + neural networks).

Conclusion

Based on machine learning analysis of HAMD-24 data from 374 depressed patients, this study demonstrates that: 1. The ERTC model outperformed SVM, NBC, and RF in predicting suicidal ideation (accuracy: 77.75%, AUC: 0.80). Its superior robustness arose from enhanced randomization during tree construction, mitigating overfitting and improving generalization for capturing the complex interactions among HAMD-24 symptoms. This finding highlights ERTC as a particularly suitable algorithm for modeling complex symptom interactions within clinical scale data, contrasting with some prior studies favoring SVM or RF for similar tasks.^13,15 2. Critical predictors of suicidal ideation within the HAMD-24 (excluding Item 3) included feelings of despair, guilt, inferiority, loss of work/interest, and overall depressive mood. This granular identification and ranking of specific depressive symptoms as primary drivers of suicide ideation, validated by machine learning, provides a more nuanced understanding than simply associating overall depression severity (HAMD total score) with risk.^29,30 While despair ranked highest in feature importance, its quantitative lead over guilt and inferiority was marginal, suggesting these core symptoms collectively drive risk within the scale framework. 3. The quantification of the relative importance of specific HAMD-24 symptoms offers a novel, data-driven theoretical foundation for refining existing depression-suicide risk assessment scales or developing new, more targeted ones, moving beyond simply confirming associations to informing how specific symptoms contribute mechanistically to suicide ideation within the depression construct. Clinicians should prioritise cognitive-restructuring interventions targeting despair, guilt and inferiority; risk-stratify patients using an 80% probability cut-off from the ERTC model; and consider supplementing HAMD-24 screening with momentary ambivalence assessments for high-risk individuals.

Data Sharing Statement

The de-identified datasets (demographics, HAMD-24 item scores excluding Item 3, BSI-CV group labels) and Python code used for preprocessing, model training, and evaluation are available from the corresponding author on reasonable request under a data sharing agreement that ensures participant confidentiality and compliance with ethical guidelines.

Ethics Approval and Consent to Participate

This study was conducted in accordance with the declaration of Helsinki. This study was conducted with approval from the Ethics Committee of Nanjing Medical University Affiliated Changzhou Second People’s Hospital. A written informed consent was obtained from all participants.

Author Contributions

Conception and design of the research: Yun Chen; Guan-Zhong Dong; Acquisition of data: Yun Chen; Guan-Zhong Dong; Wei-Yuan Zhang; Ke Wang; Analysis and interpretation of the data: Zhong-Yi Jiang, Ke Wang; Statistical analysis: Zhong-Yi Jiang, Wei-Yuan Zhang; Obtaining financing: Hai-Yan Yang; Ke Wang; Writing of the manuscript: Yun Chen; Critical revision of the manuscript for intellectual content: Hai-Yan Yang. All authors made a significant contribution to the work reported, whether that is in the conception, study design, execution, acquisition of data, analysis and interpretation, or in all these areas; took part in drafting, revising or critically reviewing the article; gave final approval of the version to be published; have agreed on the journal to which the article has been submitted; and agree to be accountable for all aspects of the work.

Disclosure

None of the authors have any financial disclosure or conflicts of interest to report for this work.

References

1. Wang G, Feng Y, Liu J, et al. Chinese guidelines for the prevention and treatment of depression (2024 Edition) proposal. Chin Psychiatry Miscellaneous Zhi. 2023;56(6):407–412. doi:10.3760/cma.j.cn113661-20230919-00076

2. Huang Y, Wang YU, Wang H, et al. Prevalence of mental disorders in China: a cross-sectional epidemiological study. Lancet Psychiatry. 2019;6(3):211–224.

3. Dong M, Wang SB, Li Y, et al. Prevalence of suicidal behaviors in patients with major Depressive disorder in China: a comprehensive meta-analysis. J Affect Disord. 2018;225:32–39.

4. Orsolini L, Latini R, Pompili M, et al. Understanding the complex of suicide in depression: from research to clinics. Psychiatry Invest. 2020;17(3):207–221.

5. Fava GA, Kellner R, Munari F, Pavan L. The Hamilton depression rating scale in normals and depressives. Acta Psychiatr Scand. 1982;66(1):26–32. PMID: 7124430. doi:10.1111/j.1600-0447.1982.tb00911.x

6. Zhang M. Handbook of Psychiatric Assessment Scales. 2nd ed. Changsha: Hunan Science and Technology Press; 1998:121–126.

7. Teismann T, Siebert AM, Forkmann T. Suicidal ambivalence: a scoping review. Suicide Life Threat Behav. 2024;54(5):802–813. PMID: 38709556. doi:10.1111/sltb.13092

8. Ernst M, Gemke TJ, Olivi LJ, O’Connor RC. Ambulatory assessment of suicidal ambivalence: the temporal variability of the wish to live and the wish to die and their relevance in the concurrent and prospective prediction of suicidal desire. Suicide Life Threat Behav. 2024;54(5):831–843. PMID: 39096098. doi:10.1111/sltb.13120

9. Hogoboom A, Rouch M, Lauerman D, Pauselli L, Compton MT. Initial evidence of vowel space reduction in a subset of individuals with schizophrenia. Schizophr Res. 2023;255:158–164. PMID: 36989674; PMCID: PMC11371129. doi:10.1016/j.schres.2023.03.026

10. Lucarini V, Cangemi F, Daniel BD, et al. Conversational metrics, psychopathological dimensions and self-disturbances in patients with schizophrenia. Eur Arch Psychiatry Clin Neurosci. 2022;272(6):997–1005. PMID: 34476588. doi:10.1007/s00406-021-01329-w

11. Spulber S, Elberling F, Svensson J, Tiger M, Ceccatelli S, Lundberg J. Patterns of activity correlate with symptom severity in major depressive disorder patients. Transl Psychiatry. 2022;12(1):226. PMID: 35654778; PMCID: PMC9163191. doi:10.1038/s41398-022-01989-9

12. Petrosellini C, Eriksson SH, Meyer N, et al. Sleep disturbance as a marker of postpartum psychosis risk: a prospective actigraphy study. BMC Psychiatry. 2025;25(1):569. PMID: 40457330; PMCID: PMC12131421. doi:10.1186/s12888-025-07017-6

13. Lu J, Li L, Xu X. Interpretation of the Chinese guidelines for the prevention and treatment of depression (Second Edition): evaluation and diagnosis. Chin Psychiatry J. 2017;50(3):169–171.

14. Maatoug R, Gorwood P. The psychometrics of the hospital anxiety and depression scale supports a shorter −12 item- version. Psychiatry Res. 2019;274:372–376. PMID: 30852430. doi:10.1016/j.psychres.2019.02.074

15. Kim HJ, Kim S, Son Y, Youn I, Lee K. Reliability and validity of the Korean Version of the Ask Suicide-Screening Questions (ASQ). J Korean Med Sci. 2023;38(6):e41. PMID: 36786085; PMCID: PMC9925327. doi:10.3346/jkms.2023.38.e41

16. Yook V, Choi YH, Gu MJ, et al. Suicide Screening Questionnaire-Self-Rating (SSQ-SR): development, reliability, and validity in a clinical sample of Korean adults. Compr Psychiatry. 2023;121:152360. PMID: 36508776. doi:10.1016/j.comppsych.2022.152360

17. Linthicum KP, Schafer KM, Ribeiro JD. Machine learning in suicide science: applications and ethics. Behav Sci Law. 2019;37(3):214–222.

18. Li R. Data mining and machine learning methods for dementia re- search. Methods Mol Biol. 2018;1750:363–370.

19. Walsh CG, Ribeiro JD, Franklin JC. Predicting risk of suicide attempts over time through machine learning. Clin Psychol Sci. 2017;5(3):1032627260.

20. Miché M, Studerus E, Meyer AH, et al. Prospective prediction of suicide attempts in community adolescents and young adults, using regression methods and machine learning. J Affect Disord. 2020;265:570–578. PMID: 31786028. doi:10.1016/j.jad.2019.11.093

21. Ryu S, Lee H, Lee DK, Kim SW, Kim CE. Detection of suicide attempters among suicide ideators using machine learning. Psychiatry Invest. 2019;16(8):588–593. PMID: 31446686; PMCID: PMC6710424. doi:10.30773/pi.2019.06.19

22. Bhak Y, Jeong HO, Cho YS, et al. Depression and suicide risk prediction models using blood-derived multi-omics data. Transl Psychiatry. 2019;9(1):262. PMID: 31624227; PMCID: PMC6797735. doi:10.1038/s41398-019-0595-2

23. Yang L, Zhang Q, Bai S, et al. Using machine learning algorithms to predict the risk of suicide attempts among college students. Clin Psychol China J. 2023;31(3):525–529634. doi:10.16128/j.cnki.1005-3611.2023.03.005

24. Dong J, Wei W, Wu K, et al. The application of machine learning in the field of depression. Prog Psychol Sci. 2020;28(2):266–274. doi:10.3724/SP.J.1042.2020.00266

25. Qu J, Wu Y, Liu J, et al. Computational psychiatry: a new perspective on depression research and clinical application. Psychol Sci Prog. 2020;28(1):111–127. doi:10.3724/SP.J.1042.2020.00111

26. Lee YW, Choi JW, Shin EH. Machine learning model for predicting malaria using clinical information. Comput Biol Med. 2021;129:104151. PMID: 33290932. doi:10.1016/j.compbiomed.2020.104151

27. Karaismailoglu E, Karaismailoglu S. Two novel nomograms for predicting the risk of hospitalization or mortality due to COVID-19 by the naïve Bayesian classifier method. J Med Virol. 2021;93(5):3194–3201. PMID: 33599308; PMCID: PMC8013381. doi:10.1002/jmv.26890

28. Wallace ML, Mentch L, Wheeler BJ, et al. Use and misuse of random forest variable importance metrics in medicine: demonstrations through incident stroke prediction. BMC Med Res Methodol. 2023;23(1):144. PMID: 37337173; PMCID: PMC10280951. doi:10.1186/s12874-023-01965-x

29. Geng D, An Q, Fu Z, Wang C, An H. Identification of major depression patients using machine learning models based on heart rate variability during sleep stages for pre-hospital screening. Comput Biol Med. 2023;162:107060. PMID: 37290394; PMCID: PMC10229199. doi:10.1016/j.compbiomed.2023.107060

30. American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders. 5th ed. Beijing: Peking University Press; 2015.

31. Lin JY, Huang Y, Su YA, et al. Association between perceived stressfulness of stressful life events and the suicidal risk in Chinese patients with major depressive disorder. Chin Med J. 2018;131(8):912–919. PMID: 29664050; PMCID: PMC5912056. doi:10.4103/0366-6999.229898

32. Li X, Fei L, Zhang Y, et al. The reliability and validity of the Chinese version of the Beck Suicide Intention Scale in college students. Chin psychol J Health. 2011;25(11):862–866. doi:10.3969/j.issn.1000-6729.2011.11.013

33. Li H, Luo X, Ke X, et al. Major depressive disorder and suicide risk among adult outpatients at several general hospitals in a Chinese Han population. PLoS One. 2017;12(10):e0186143. PMID: 29016669; PMCID: PMC5634639. doi:10.1371/journal.pone.0186143

34. Ribeiro JD, Huang X, Fox KR, Franklin JC. Depression and hopelessness as risk factors for suicide ideation, attempts and death: meta-analysis of longitudinal studies. Br J Psychiatry. 2018;212(5):279–286. PMID: 29587888. doi:10.1192/bjp.2018.27

35. Buerke M, Galfalvy H, Keilp JG, et al. Age effects on clinical and neurocognitive risk factors for suicide attempt in depression – findings from the AFSP lifespan study. Affect Disord. 2021;295:123–130. PMID: 34425314; PMCID: PMC8551053. doi:10.1016/j.jad.2021.08.014

36. Simon GE, Moise N, Mohr DC. Management of depression in adults: a review. JAMA. 2024;332(2):141–152. Erratum in: JAMA. 2024;332(15):1306. doi: 10.1001/jama.2024.18427. PMID: 38856993. doi:10.1001/jama.2024.5756

37. Beck AT, Steer RA, Kovacs M, Garrison B. Hopelessness and eventual suicide: a 10-year prospective study of patients hospitalized with suicidal ideation. Am J Psychiatry. 1985;142(5):559–563. PMID: 3985195. doi:10.1176/ajp.142.5.559

38. Beck AT, Kovacs M, Weissman A. Hopelessness and suicidal behavior: an overview. JAMA. 1975;234:1146–1149.

39. Joiner T. Why People Die by Suicide. Harvard University Press; 2005.

40. Van Orden KA, Witte TK, Cukrowicz KC, Braithwaite SR, Selby EA, Joiner TE. The interpersonal theory of suicide. Psychol Rev. 2010;117(2):575–600. PMID: 20438238; PMCID: PMC3130348. doi:10.1037/a0018697

41. Abramson LY, Alloy LB, Hogan ME, et al. The hopelessness theory of suicidality. In: Joiner T, Rudd MD, editors. Suicide Science. Springer US; 2000:17–32.

42. Wenzel A, Beck AT. A cognitive model of suicidal behavior: theory and treatment. Appl Prev Psychol. 2008;12:189–201.

43. Li Y. A study on the relationship between despair, psychological resilience, and suicidal ideation among college students. Chongqing Med J. 2014;2014(5):524–526.

44. Fedina L, Nam B, Jun HJ, et al. Moderating effects of resilience on depression, psychological distress, and suicidal ideation associated with interpersonal violence. J Interpers Violence. 2021;36(3–4):NP1335–1358NP. PMID: 29295024. doi:10.1177/0886260517746183

45. Okechukwu FO, Ogba KTU, Nwufo JI, et al. Academic stress and suicidal ideation: moderating roles of coping style and resilience. BMC Psychiatry. 2022;22(1):546. PMID: 35962365; PMCID: PMC9373522. doi:10.1186/s12888-022-04063-2

46. Leonardi J, Gazzillo F, Gorman B, Bush M. Assessing Burdening Guilt and Its Correlates. Psychodyn Psychiatry. 2023;51(4):479–499. PMID: 38047672. doi:10.1521/pdps.2023.51.4.479

47. Castro NB, Lopes MVO, Monteiro ARM. Low chronic self-esteem and low situational self-esteem: a literature review. Rev Bras Enferm. 2020;73(1):e20180004. English, Portuguese. PMID: 32049223. doi:10.1590/0034-7167-2018-0004

48. Jia H, Min Z, Yiyun C, et al. Association between social withdrawal and suicidal ideation in patients with major depressive disorder: the mediational role of emotional symptoms. J Affect Disord. 2024;347:69–76. PMID: 37992770. doi:10.1016/j.jad.2023.11.051

49. Feiten JG, Mosqueiro BP, Uequed M, Passos IC, Fleck MP, Caldieraro MA. Evaluation of major depression symptom networks using clinician-rated and patient-rated data. J Affect Disord. 2021;292:583–591. PMID: 34147971. doi:10.1016/j.jad.2021.05.102

50. Kato TA, Kanba S, Teo AR. Defining pathological social withdrawal: proposed diagnostic criteria for hikikomori. World Psychiatry. 2020;19(1):116–117. PMID: 31922682; PMCID: PMC6953582. doi:10.1002/wps.20705

51. Porcelli S, Van Der Wee N, van der Werff S, et al. Social brain, social dysfunction and social withdrawal. Neurosci Biobehav Rev. 2019;97:10–33. PMID: 30244163. doi:10.1016/j.neubiorev.2018.09.012

52. Evans GW, Rhee E, Forbes C, Mata allen K, Lepore SJ. The meaning and efficacy of social withdrawal as a strategy for coping with chronic residential crowding. J Environ Psychol. 2000;20:335–342.

53. Zhu S, Lee PH, Wong PWC. Investigating prolonged social withdrawal behaviour as a risk factor for self-harm and suicidal behaviours. BJPsych Open. 2021;7(3):e90. PMID: 33926603; PMCID: PMC8142544. doi:10.1192/bjo.2021.47

54. Iweama CN, Agbaje OS, Lerum NI, Igbokwe CC, Ozoemena LE. Suicidal ideation and attempts among Nigerian undergraduates: exploring the relationships with depression, hopelessness, perceived burdensomeness, and thwarted belongingness. SAGE Open Med. 2024;12:20503121241236137. PMID: 38533197; PMCID: PMC10964440. doi:10.1177/20503121241236137

55. Winstone L, Heron J, John A, et al. Ecological momentary assessment of self-harm thoughts and behaviors: systematic review of constructs from the integrated motivational-volitional model. JMIR Ment Health. 2024;11:e63132. PMID: 39652869; PMCID: PMC11667137. doi:10.2196/63132

56. Wenzel J, Dreschke N, Hanssen E, et al. Ecological momentary assessment (EMA) combined with unsupervised machine learning shows sensitivity to identify individuals in potential need for psychiatric assessment. Eur Arch Psychiatry Clin Neurosci. 2024;274(7):1639–1649. Erratum in: Eur Arch Psychiatry Clin Neurosci. 2025;275(3):959–962. doi: 10.1007/s00406-024-01939-0. PMID: 37715784; PMCID: PMC11422424. doi:10.1007/s00406-023-01668-w

57. Lebowitz ER, François B. Using motion tracking to measure avoidance in children and adults: psychometric properties, associations with clinical characteristics, and treatment-related change. Behav Ther. 2018;49(6):853–865. PMID: 30316485; PMCID: PMC6394864. doi:10.1016/j.beth.2018.04.005

58. Kagawa F, Yokoyama S, Takamura M, et al. Decreased physical activity with subjective pleasure is associated with avoidance behaviors. Sci Rep. 2022;12(1):2832. PMID: 35181696; PMCID: PMC8857298. doi:10.1038/s41598-022-06563-3

Stay informed with free updates

Simply sign up to the Pharmaceuticals sector myFT Digest — delivered directly to your inbox.

Incoming GSK chief executive Luke Miels is under pressure to boost investor confidence in the pharmaceutical group’s drug pipeline, following years of market scepticism under current boss Emma Walmsley.

Miels, a 50-year-old Australian, will take over the UK-listed drugmaker at the start of next year when Walmsley steps down. After eight years as chief commercial officer, he is known for his sharp execution and knack for uncovering “hidden gem” acquisitions. 

One top five investor said Miels had an “opportunity to reward shareholders”.

Walmsley has previously said she is confident GSK can navigate patent expiries in its HIV business towards the end of the decade and that annual revenue will increase from £31bn in 2024 to £40bn by 2031. But she has struggled to convince many investors. GSK’s share price has fallen about 10 per cent during her tenure and analysts forecast annual revenues of £33bn by 2031.

“I do believe [Miels] will be more convincing than Emma with the market,” the shareholder said. “He has had a successful track record before GSK. And he has proper ownership of his pipeline and he will now be in charge of asset allocation,” they added.  

Miels has previously worked at AstraZeneca, Roche and Sanofi. GSK shares rose more than 3 per cent on the day his appointment was announced.

The shareholder added that Miels would be judged on whether he can hit the £40bn sales target, but also needed to deliver “some milestones along the way so that people can gain comfort that GSK is on track”. 

Another shareholder said Miels had enough time before major patent expiries to deliver results, calling this a “strength of the succession process”.

“The key driver remains execution on the drug pipeline,” they said, adding that success in pharma was “essentially binary”. Companies that prove they can discover effective drugs trade on much higher price/earnings multiples. 

Miels came to GSK from AstraZeneca, where he had been close to chief executive Pascal Soriot. AstraZeneca sued for violation of his contract and court documents reported by the Sunday Times at the time said Soriot told Miels he could leave for any company but GSK. 

Since then, GSK has hired other staff from its UK rival, including key members of its M&A team. 

Miels has made dealmaking a major part of his job, devoting at least a day a week to it. He has championed the acquisition of under-appreciated assets that have become successful products, including a blood cancer drug and an antibiotic to treat urinary tract infections.

One executive close to Miels said he is willing to cut programmes that are not performing but happy to commit money to those he thinks have potential, including the antibiotic when there were many internal doubters. “The pace of business development will continue or take another step up in the next two or three years,” the executive said. 

Unlike Walmsley, who was criticised by activist investor Elliott Management for not having a scientific background, Miels has an undergraduate degree in science. He has spent his career on the commercial side of the business, but works closely with GSK’s chief scientific officer Tony Wood, who runs research and development.  

“He loves going toe to toe with R&D, and he loves the science,” the executive said. 

When Miels was appointed, GSK chair Sir Jonathan Symonds commented on his “outstanding global biopharma development and commercial experience”.

But another executive who worked with him earlier in his career said Miels could be “more than hyper focused” on the commercial plans but did not have a “passion for science”.

Announcing the appointment, Walmsley said she was “extremely pleased” with the smooth succession process. She said that when she started putting together her team in late 2016, she wrote in her diary that Miels would be a “dream appointment”. 

“All these years later, I absolutely couldn’t be more delighted that he’s picking up the baton.” 

 

But as expectations rise and the pace of change accelerates, a critical question emerges: at what cost? The drive to keep up with innovation and deliver results can stretch leaders and teams to their limits, putting their well-being and resilience at risk. Burnout is not a distant concern—it’s a real and pressing challenge in today’s boardrooms and beyond.

The forces at play

The modern boardroom is being called to step up with agility and foresight. Directors’ roles are growing in scope and complexity—no longer limited to monitoring and compliance, but demanding decisive, visionary leadership in the face of uncertainty. Their bandwidth to focus on consequential decisions, rather than being consumed by reactive decision-making, is under pressure. 

Perhaps nowhere is this more evident than with the rise of AI, which exemplifies both the opportunity and complexity boards must navigate. Deloitte’s latest survey reveals AI’s rapid rise is fueling a readiness to evolve: 53% of C-suite leaders want to accelerate AI adoption—but 66% say their boards lack sufficient knowledge or experience. The board’s challenge lies in deepening their expertise while being intentional about protecting their bandwidth given the sheer volume of information and pace of change. 

But technology is only part of the story. The future of work is evolving on multiple fronts, and boards must also balance the drive for innovation with the workforce’s desire for stability. Deloitte’s 2025 Global Human Capital Trends report introduces “stagility”—stability and agility—as an essential leadership capability. While 75% of workers hope for more stability, 85% of executives are willing to embrace change and focus on becoming agile as they adapt to rapid transformations. It’s the board’s responsibility to be aware of this tension and provide thoughtful oversight to help organizations strike the right balance. 

The strain and pressures directors are experiencing in the boardroom mirror the broader societal and systemic forces shaping today’s environment. While many factors are outside the board’s control, the opportunity to set the tone for well-being as an imperative—not a nice to have—can start with us. Modern leadership means championing both business and human outcomes. By prioritizing purposeful, resilient governance, we can help safeguard our bandwidth, inspire broader organizational well-being, and enable high-impact decision-making at scale. 

Intent over habit: governing at scale

You may be thinking, “yes, but how?” The answer may lie in anchoring board practices in clear purpose and adaptable structures. Too often, boards fall into the trap of doing things “the way they’ve always been done.” As stewards of the organization, directors often equate tradition with stability—especially when pressure and stakes are high. But many of today’s organizations look very different than at their inception—and governance practices should reflect that evolution.

To unlock the art of the possible, it’s important to commit to governance at scale, moving beyond traditional practices to meet the complexities of modern business. This means zeroing in on what truly drives value: establishing clear priorities. Leveraging technology and streamlining processes can enable boards to run efficient meetings and direct their attention to consequential issues—protecting bandwidth and empowering leaders to embrace “stagility.”

Governing at scale doesn’t require complicated solutions. Streamlining agendas and providing concise pre-read materials can allow directors to prepare thoughtfully and focus on strategic issues. Maximizing schedules by incorporating virtual or hybrid meeting formats can enable directors to stay refreshed and attentive, so they can contribute meaningfully. Bringing in outside experts for focused education sessions can expose directors to fresh perspectives and equip them to navigate emerging challenges with greater confidence. With the right guardrails, integrating AI and other emerging technologies can help boards decode complex issues faster, accelerate upskilling, and enhance decision-making. When directors are supported by intentional, streamlined board processes, they can gain the clarity and confidence to stay engaged and energized—enabling high-impact governance that inspires innovation, nurtures resilience, and drives sustainable growth.

The path forward

Prioritizing these practices at the highest levels is about more than just wellness; it can be a strategic advantage. The health of the boardroom is intrinsically linked to the health of the organization. Especially as AI and other forces reshape the landscape, organizations that invest in their board’s capacity to adapt and govern at scale can be better equipped to navigate disruption and shape the future with decisive, agile oversight.

Let’s commit to showing up authentically, supporting one another, and governing with intention and care. By embracing new ways of working and optimizing bandwidth, boardrooms and organizations can not only endure disruption, but capitalize on change. And while the path to resilience is ongoing, finding ways to track and evaluate it—just as we do with other key performance indicators—may be an essential step toward true accountability and sustained performance. Turn today’s challenges into tomorrow’s opportunities and help ensure your organizations remain resilient, innovative, and ready for whatever comes next. 

This publication contains general information only and Deloitte is not, by means of this publication, rendering accounting, business, financial, investment, legal, tax, or other professional advice or services. This publication is not a substitute for such professional advice or services, nor should it be used as a basis for any decision or action that may affect your business. Before making any decision or taking any action that may affect your business, you should consult a qualified professional advisor. Deloitte shall not be responsible for any loss sustained by any person who relies on this publication.

Copyright © 2025 Deloitte Development LLC. All rights reserved.

The opinions expressed in Fortune.com commentary pieces are solely the views of their authors and do not necessarily reflect the opinions and beliefs of Fortune.

Fortune Global Forum returns Oct. 26–27, 2025 in Riyadh. CEOs and global leaders will gather for a dynamic, invitation-only event shaping the future of business. Apply for an invitation.

Welcome to OncLive®’s OncFive!

Every week, we bring you a quick roundup of the 5 top stories from the world of oncology—ranging from pivotal regulatory decisions to key pipeline updates to expert insights on breakthroughs that are moving the needle in cancer care. This resource is designed to keep you informed on the latest updates in the space, in just a matter of minutes.

Here’s what you may have missed this week:

The FDA cleared cemiplimab-rwlc (Libtayo) for adjuvant use in adult patients with cutaneous squamous cell carcinoma (CSCC) at high risk of recurrence after surgery and radiation. The decision was supported by findings from the phase 3 C-POST trial (NCT03969004), in which cemiplimab reduced the risk of recurrence or death by 68% vs placebo (HR, 0.32; 95% CI, 0.20-0.51; P < .0001), with median disease-free survival not reached in the cemiplimab arm. Recurrence occurred in 9% of patients in the cemiplimab arm vs 30% of those in the placebo arm. The toxicity profile was consistent with prior findings, with common adverse effects (AEs) including rash, pruritus, and hypothyroidism. The decision signifies the first and only immunotherapy approved for adjuvant treatment in those with CSCC with a high risk of recurrence following surgery and radiation.

The FDA has issued a complete response letter (CRL) to the new drug application (NDA) for dasatinib (Dasynoc) for use in patients with chronic myeloid leukemia (CML). The CRL stems from Good Manufacturing Practice observations at the company’s contract manufacturing site, prompting a temporary pause in new product approvals until corrective actions are completed. The manufacturer has begun remediation efforts and plans to meet with the regulatory agency later this year to address outstanding issues. The NDA for dasatinib sought approval for a formulation designed to maintain efficacy at lower doses, reduce pharmacokinetic variability, and minimize drug-drug interactions associated with acid-suppressive agents. Despite manufacturing delays, the drug remains under active development, with plans for expedited resubmission once compliance measures are met.

The regulatory agency also accepted and granted priority review to the biologics license application (BLA) seeking approval of Orca-T for select patients with acute myeloid leukemia (AML), acute lymphoblastic leukemia (ALL), and myelodysplastic syndrome (MDS). The application is supported by data from the phase 3 Precision-T trial (NCT04013685), in which Orca-T significantly improved 1-year moderate-to-severe chronic graft-vs-host disease (cGVHD)–free survival vs conventional allogeneic hematopoietic stem cell transplant (allo-HSCT; 78% vs 38%; HR, 0.26; P < .00001). Those who received Orca-T also experienced lower rates of moderate-to-severe cGVHD (13% vs 44%) and grade 3/4 acute GVHD (6% vs 17%) vs allo-HSCT. One-year overall survival (OS) was 94% in the Orca-T arm and 83% in the allo-HSCT arm, and non-relapse mortality rates were 3% vs 13%, respectively. The target action date for the BLA is set for April 6, 2026.

Data from the phase 3 TROPION-Breast02 trial (NCT05374512) showed that datopotamab deruxtecan-dlnk (Dato-DXd; Datroway) significantly improved OS and progression-free survival (PFS) vs investigator’s choice of chemotherapy in patients with locally recurrent, inoperable, or metastatic triple-negative breast cancer (TNBC) not able to receive immunotherapy. The safety profile of Dato-DXd was consistent with prior breast cancer studies. AstraZeneca and Daiichi Sankyo will share these results with regulatory authorities, highlighting the potential of the antibody-drug conjugate as the first therapy to significantly improve OS in this population.

The FDA has granted fast track designation to the TEAD autopalmitoylation inhibitor VT3989 for use in patients with unresectable malignant pleural or non-pleural mesothelioma who have progressed after previous immune checkpoint inhibition and platinum-based chemotherapy. Preliminary findings from an ongoing phase 1/2 trial (NCT04665206) demonstrated that the agent led to reductions in target lesion size in both pleural and non-pleural mesothelioma, irrespective of NF2 mutational status. The multicenter trial includes dose-escalation, dose-expansion, and combination cohorts, which are evaluating safety, antitumor activity, and pharmacokinetics of the agent, with oral dosing ranging from 25 mg to 200 mg. Common treatment-related AEs included albuminuria, proteinuria, fatigue, peripheral edema, and gastrointestinal and hepatic effects.

Honorable Mentions

• OncLive spoke with the following leading genitourinary oncology experts to highlight the most anticipated abstracts and data at the 2025 ESMO Congress: David A. Braun, MD, PhD, of Yale Medical School; Alan Tan, MD, of Vanderbilt University Medical Center; and Axel Merseburger, MD, PhD, of University Hospital Schleswig-Holstein. Check out the exclusive preview ahead of the meeting.
• From further clarifying the role of PD-(L)1 inhibition in gastric cancer and colorectal cancer, to demonstrating the potential predictive value of minimal residual disease negativity in late-stage colon cancer, gastrointestinal oncology data presented at the 2025 ESMO Congress are anticipated to challenge current standards of care and bring new questions to the forefront of research in the field. In this exclusive preview, Tanios S. Bekaii-Saab, MD, of Mayo Clinic; Suneel Kamath, MD, of Cleveland Clinic Lerner College of Medicine of Case Western Reserve University; and Kanwal P. S. Raghav, MBBS, MD, of The University of Texas MD Anderson Cancer Center, share their most anticipated abstracts.

Less than 10 years after dropping out of New York University and then starting what would become the prediction market Polymarket in the bathroom of his Lower East Side apartment, Shayne Coplan has been crowned the youngest ever self-made billionaire by capitalizing on Gen Z’s readiness to bet on anything.

On Tuesday, the New York Stock Exchange’s parent company, Intercontinental Exchange, invested $2 billion cash in Polymarket, skyrocketing the company’s valuation to $9 billion post investment and making CEO and founder Coplan a billionaire at the age of 27, according to the Bloomberg Billionaire Index.

Through the partnership, the NYSE will distribute Polymarket’s data and the two companies will work together on tokenization initiatives, according to a press release.

Polymarket has a simple premise: Markets are the best way to source truth. By giving users a stake in predicting literally everything, from the 2025 World Series Champion to when the government shutdown will end (both bets are currently available on its website), Polymarket aims to “harness the power of free markets to demystify real events that matter most to you,” Coplan said in a post on X.

Polymarket matches users with opposing bets and pays out $1 per “share” for every correct guess with the help of a U.S. dollar-backed stablecoin and a blockchain built on top of Ethereum’s infrastructure. This means if you bet “yes” on an outcome at 37 cents and it proves to be true, you’ll net a 63-cent profit. You can also sell your stake in an outcome before the event happens, which can also net you a profit if the price of your shares go up as the outcome you chose becomes more likely.

Aleksandar Tomic, an economist and associate dean for strategy, innovation, and technology at Boston College, said prediction markets like Polymarket have existed before. A similar platform, Intrade, received widespread media attention for its success in predicting the 2008 and 2012 U.S. elections before shutting down in 2013. Polymarket and its competitors seem to be succeeding where others have failed. Polymarket for its part has drawn in younger users with a better platform and by seizing upon the pandemic-era gambling trend especially prevalent in Gen Z men—not to mention with a little help from a newly friendly regulatory environment.

“I think these types of markets are just another place to make a bet,” Tomic told Fortune.

Polymarket did not immediately respond to a request for comment.

Until last month, Polymarket was banned in the U.S., largely due to federal regulators’ objections to its “speed over scrutiny” business model. In 2022, the company paid a $1.4 million fine after the Commodity Futures Trading Commission (CFTC) said it was allegedly operating an unregistered event market. The platform was subsequently barred from the country. As wagers on the 2024 election grew last year, the CFTC renewed its scrutiny, and the FBI raided founder Shayne Coplan’s home in November. Just under a year later—following President Trump’s return to office, and with Donald Trump Jr. now serving as an adviser to the company—the CFTC and Justice Department closed their investigations without filing charges, clearing the way for Polymarket’s return to the U.S.

Despite Polymarket’s many headwinds over the years, Coplan has previously pointed out some of the company’s notable successes on X, including predicting that President Biden would drop out of the 2024 presidential election. In total, Polymarket users put at least $3.2 billion into the presidential election, and one French trader even made around $85 million from his contrarian multimillion-dollar bet that President Donald Trump would return to the Oval Office.

With this week’s announcement of the team-up and investment from the New York Stock Exchange’s parent company, Coplan is riding high, while still reflecting on his journey upwards.

“At the onset of the pandemic, I quite literally had nothing to lose: 21, running out of money, 2.5 years since I dropped out and nothing to show for it,” he wrote on X. “But I knew we were entering an era where ways to find truth would matter more than ever, and Polymarket could play a critical role in that.”

On Sunday, he plans to watch football and beta-test the new Polymarket U.S. app, he wrote on X.

This story was originally featured on Fortune.com