{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T15:03:42Z","timestamp":1790348622419,"version":"4.1.0"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>College students\u2019 psychological vulnerability assessment is constrained by data scarcity, high labeling cost, privacy sensitivity, and small, imbalanced samples, and existing frameworks typically treat vulnerability as a static judgment that cannot track how a student\u2019s condition changes over time. This study examined whether a few-sample hierarchical grading model combined with meta-reinforcement-learning-based sequential decision-making could address both problems jointly.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A few-sample hierarchical grading model, combining meta-learning and transfer regularization with a prototype-based embedding and ordinal threshold assignment, quantified static risk from a handful of labeled examples per grade, while a sequential risk-identification method formulated dynamic assessment as a Markov decision process solved by a two-stage meta-reinforcement-learning policy. Case studies used a longitudinal, class-imbalanced cohort simulation calibrated to the documented statistics of a mobile-sensing mental-health study (no real participant data were used) and compared the proposed models against threshold-rule, supervised, fine-tuned, few-shot, and non-meta reinforcement-learning baselines, with sensitivity analyses on support-set size, reward weights, discount factor, and regularization weight, plus a regime-switching robustness check.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed grading model attained a macro-F1 of 0.847 with ten labeled examples per grade, over twenty percentage points above a conventional deep-learning classifier, though its edge over other episodic few-shot architectures was small and inconsistent, indicating episodic meta-learning as the main source of this gain. The meta-reinforcement-learning policy achieved a higher alert precision-recall area (0.514 vs. 0.380) than a non-meta baseline and avoided its degenerate always-escalate behavior, but neither the main study nor the regime-switching check showed the composite reward lengthening lead time versus a simpler accuracy-only reward, which matched its lead time at a much lower escalation rate. Sensitivity analyses showed the reward-weight ratio and discount factor shaping the early-identification versus intervention-cost trade-off.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These findings suggest that combining few-sample meta-learning with metareinforcement-learning-based sequential decision-making can improve vulnerability assessment under scarce, evolving data relative to conventional static and non-meta-adapted approaches, with an accuracy-only reward recommended as the practical default. The case studies relied on a calibrated simulation rather than raw longitudinal records, so prospective validation on real campus data under appropriate privacy safeguards is needed before responsible deployment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2026.1932839","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T14:36:36Z","timestamp":1790346996000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Intelligent vulnerability assessment system for college students mental health based on few-sample reinforcement learning approach"],"prefix":"10.3389","volume":"17","author":[{"given":"Xiaobo","family":"Huang","sequence":"first","affiliation":[{"name":"Student Management Section, Office of Student Affairs, Nantong University","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayue","family":"Ji","sequence":"additional","affiliation":[{"name":"Student Management Section, Office of Student Affairs, Nantong University","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Nantong University","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2025.01.107","article-title":"Health risk behaviors, depressive symptoms and suicidal ideation among college students: A latent class analysis in middle China","volume":"375","author":"Xiang","year":"2025","journal-title":"J Affect Disord"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1186\/s12889-025-22669-5","article-title":"The impact of COVID-19 quarantine on college students\u2019 mental health","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Public Health"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s10734-023-01009-9","article-title":"Student mental health and dropout from higher education: an analysis of Australian administrative data","volume":"87","author":"Zaja\u02dbc","year":"2024","journal-title":"High Educ"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1177\/08959048211015613","article-title":"The creation of a mental health policy in higher education","volume":"36","author":"Pilato","year":"2022","journal-title":"Educ Policy"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-025-13352-8","article-title":"Technology-driven support: exploring the impact of artificial intelligence on mental health in higher education","volume":"30","author":"Zhai","year":"2025","journal-title":"Educ Inf Technol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1186\/s40359-024-01808-4","article-title":"Rethinking students\u2019 mental health assessment through GHQ-12: evidence from the IRT approach","volume":"12","author":"Comotti","year":"2024","journal-title":"BMC Psychol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1136\/bjsports-2021-105136","article-title":"Internal consistency reliability of mental health questionnaires in college student athletes","volume":"57","author":"Taylor","year":"2023","journal-title":"Br J Sports Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.jad.2022.05.065","article-title":"Using network analysis to identify central symptoms of college students\u2019 mental health","volume":"311","author":"Ma","year":"2022","journal-title":"J Affect Disord"},{"key":"B9","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s13034-024-00734-y","article-title":"Potential mental health-related harms associated with the universal screening of anxiety and depressive symptoms in Australian secondary schools","volume":"18","author":"Braund","year":"2024","journal-title":"Child Adolesc Psychiatry Ment Health"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.2196\/80662","article-title":"Using ultra-abridged individual difference scales for personalization in digital mental health to improve uptake, engagement, and experiences: three-tiered decision framework for scale shortening","volume":"28","author":"Yeung","year":"2026","journal-title":"J Med Internet Res"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2025.120679","article-title":"Mental health at risk: predicting psychological distress in Australian youth through machine learning models","volume":"395","author":"Ahammed","year":"2026","journal-title":"J Affect Disord"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2024.09.111","article-title":"Machine learning-enabled mental health risk prediction for youths with stressful life events: a modelling study","volume":"368","author":"Ding","year":"2025","journal-title":"J Affect Disord"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01811-5","article-title":"Machine learning model to predict mental health crises from electronic health records","volume":"28","author":"Garriga","year":"2022","journal-title":"Nat Med"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/s10964-023-01767-w","article-title":"Predicting adolescent mental health outcomes across cultures: a machine learning approach","volume":"52","author":"Rothenberg","year":"2023","journal-title":"J Youth Adolesc"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3547753","article-title":"Stress severity detection in college students using emotional pulse signals and deep learning","volume":"16","author":"Li","year":"2025","journal-title":"IEEE Trans Affect Comput"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2024.3413175","article-title":"Automatic depression detection among higher education students based on DeepFM","volume":"73","author":"Ruan","year":"2024","journal-title":"IEEE Trans Instrum Meas"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jare.2026.05.050","article-title":"Predicting risk of mental health deterioration using multimodal data from the UK biobank","author":"Yang","year":"2026","journal-title":"J Adv Res"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2025.3550419","article-title":"Deep learning-driven behavioral modeling in IoST for mental health monitoring and intervention","volume":"13","author":"Li","year":"2026","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2026.133395","article-title":"Digitally analyzing psychological data for mental health prediction: a comprehensive review on depression and suicide detection","volume":"681","author":"Shah","year":"2026","journal-title":"Neurocomputing"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/jbhi.2025.3594133","article-title":"MentalQLM: a lightweight large language model for mental healthcare based on instruction tuning and dual LoRA modules","volume":"30","author":"Shi","year":"2025","journal-title":"IEEE J BioMed Health Inform"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4749465","article-title":"PBDD: a prompt-based learning approach for few-shot social media depression detection","volume":"13","author":"Wang","year":"2026","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"B22","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/s41746-025-01969-5","article-title":"Optimizing large language models for detecting symptoms of depression\/anxiety in chronic diseases patient communications","volume":"8","author":"Kim","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2026.1790533","article-title":"Depression subtype classification from social media posts: few-shot prompting vs. fine-tuning of large language models","volume":"8","author":"AlSaad","year":"2026","journal-title":"Front Digit Health"},{"key":"B24","doi-asserted-by":"publisher","first-page":"987","DOI":"10.3724\/sp.j.1041.2025.0987","article-title":"Suicidal ideation data augmentation and recognition technology based on large language models","volume":"57","author":"Zhang","year":"2025","journal-title":"Acta Psychol Sin"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.2196\/66907","article-title":"Multimodal multitask learning for predicting depression severity and suicide risk using pretrained audio and text embeddings: methodology development and application","volume":"13","author":"Hu","year":"2025","journal-title":"JMIR Med Inform"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2021.3109485","article-title":"Few-shot learning in emotion recognition of spontaneous speech using a siamese neural network with adaptive sample pair formation","volume":"14","author":"Feng","year":"2023","journal-title":"IEEE Trans Affect Comput"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.109644","article-title":"Uncertainty-aware variational soft prompt for few-shot tuning in fMRI-based mental state decoding","volume":"117","author":"Hu","year":"2026","journal-title":"BioMed Signal Process Control"},{"key":"B28","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1109\/rbme.2024.3492381","article-title":"A survey of few-shot learning for biomedical time series","volume":"18","author":"Li","year":"2025","journal-title":"IEEE Rev BioMed Eng"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1097\/ccm.0000000000006100","article-title":"Does reinforcement learning improve outcomes for critically ill patients? a systematic review and level-of-readiness assessment","volume":"52","author":"Otten","year":"2024","journal-title":"Crit Care Med"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2023.3331847","article-title":"Interpretable disease progression prediction based on reinforcement reasoning over a knowledge graph","volume":"54","author":"Sun","year":"2024","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"B31","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s13012-022-01239-y","article-title":"Stepped implementation-to-target: a study protocol of an adaptive trial to expand access to addiction medications","volume":"17","author":"Ford","year":"2022","journal-title":"Implement Sci"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1128\/msystems.00018-23","article-title":"Bayesian sequential approach to monitor COVID-19 variants through test positivity rate from wastewater","volume":"8","author":"Cricelio Montesinos-L\u00f3pez","year":"2023","journal-title":"mSystems"},{"key":"B33","doi-asserted-by":"publisher","first-page":"126708","DOI":"10.2139\/ssrn.5023192","article-title":"Cost-sensitive reinforcement learning for credit risk","volume":"272","author":"C-Rella","year":"2025","journal-title":"Expert Syst Appl"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2025.147318","article-title":"Risk identification and prediction of corporate low-carbon transition via multi-agent reinforcement learning: using OpenEI and CDP database","volume":"538","author":"Hu","year":"2026","journal-title":"J Clean Prod"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122173","article-title":"SSL-ProtoNet: self-supervised learning prototypical networks for few-shot learning","volume":"238","author":"Lim","year":"2024","journal-title":"Expert Syst Appl"},{"key":"B36","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1016\/j.ejor.2023.05.007","article-title":"Probabilistic ordinal regression methods for multiple criteria sorting admitting certain and uncertain preferences","volume":"311","author":"Ru","year":"2023","journal-title":"Eur J Oper Res"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1109\/lwc.2026.3668310","article-title":"Meta-reinforcement learning for fast and data-efficient spectrum allocation in dynamic wireless networks","volume":"15","author":"Giwa","year":"2026","journal-title":"IEEE Wireless Commun Lett"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/tevc.2025.3529503","article-title":"Zeroth-order actor-critic: an evolutionary framework for sequential decision problems","volume":"29","author":"Lei","year":"2025","journal-title":"IEEE Trans Evol Comput"},{"key":"B39","first-page":"3","article-title":"Studentlife: assessing mental health, academic performance and behavioral trends of college students using smartphones","author":"Wang","year":"2014"},{"key":"B40","article-title":"studentlife: tidy handling and navigation of the Student-Life mHealth dataset","volume-title":"Github Repository","year":"2025"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2023.3303367","article-title":"Offline deep reinforcement learning and off-policy evaluation for personalized basal insulin control in type 1 diabetes","volume":"27","author":"Zhu","year":"2023","journal-title":"IEEE J BioMed Health Inform"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3390\/ai5010020","article-title":"Few-shot fine-grained image classification: a comprehensive review","volume":"5","author":"Zhang","year":"2024","journal-title":"AI"},{"key":"B43","doi-asserted-by":"publisher","first-page":"183","DOI":"10.31234\/osf.io\/km37w","article-title":"Advancing the network theory of mental disorders: a computational model of panic disorder","volume":"131","author":"Robinaugh","year":"2024","journal-title":"Psychol Rev"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127053","article-title":"Layerwise-priority-based gradient adjustment for few-shot learning","volume":"275","author":"Kim","year":"2025","journal-title":"Expert Syst Appl"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10010149","article-title":"An explainable machine learning approach for COVID-19\u2019s impact on mood states of children and adolescents during the first lockdown in Greece","volume":"10","author":"Ntakolia","year":"2022","journal-title":"Healthcare"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2025.116607","article-title":"Interpretable machine learning approach for predicting clinically significant suicide risk: a case study of patients with major depressive disorder in Greece","volume":"351","author":"Ntakolia","year":"2025","journal-title":"Psychiatry Res"},{"key":"B47","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1186\/s12888-026-07901-9","article-title":"Identifying past-year self-reported suicidality in outpatients with somatic symptom disorder using an interpretable machine-learning model: a multicenter study with an online calculator","volume":"26","author":"Wang","year":"2026","journal-title":"BMC Psychiatry"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1932839\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T14:36:37Z","timestamp":1790346997000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1932839\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":47,"alternative-id":["10.3389\/fpsyt.2026.1932839"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2026.1932839","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"article-number":"1932839"}}