{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T17:18:59Z","timestamp":1789060739320,"version":"build-2803163510"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission, Adminitrative Commission of Zhongguancun Science Park","doi-asserted-by":"publisher","award":["Z191100006619104"],"award-info":[{"award-number":["Z191100006619104"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016126","name":"Beijing Hospital Authority","doi-asserted-by":"publisher","award":["DFL20192001"],"award-info":[{"award-number":["DFL20192001"]}],"id":[{"id":"10.13039\/100016126","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["7242077"],"award-info":[{"award-number":["7242077"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Asian Journal of Psychiatry"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1016\/j.ajp.2025.104707","type":"journal-article","created":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T03:07:09Z","timestamp":1759547229000},"page":"104707","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Can AI replace clinician-rated depression scales? The psychometric properties of HAMLET \u2013 Hamilton Large-Language-Model Evaluation Tool"],"prefix":"10.1016","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3570-211X","authenticated-orcid":false,"given":"Wen","family":"Xin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huailiang","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanxiao","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1265-5093","authenticated-orcid":false,"given":"Shuping","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ajp.2025.104707_bib1","doi-asserted-by":"crossref","first-page":"2163","DOI":"10.1176\/appi.ajp.161.12.2163","article-title":"The hamilton depression rating scale: has the gold standard become a lead weight?","volume":"161","author":"Bagby","year":"2004","journal-title":"Am. J. Psychiatry"},{"key":"10.1016\/j.ajp.2025.104707_bib2","unstructured":"Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., Fan, Y., Ge, W., Han, Y., Huang, F., Hui, B., Ji, L., Li, M., Lin, J., Lin, R., Liu, D., Liu, G., Lu, C., Lu, K., Ma, J., Men, R., Ren, Xingzhang, Ren, Xuancheng, Tan, C., Tan, S., Tu, J., Wang, P., Wang, S., Wang, W., Wu, S., Xu, B., Xu, J., Yang, A., Yang, H., Yang, J., Yang, S., Yao, Y., Yu, B., Yuan, H., Yuan, Z., Zhang, J., Zhang, X., Zhang, Y., Zhang, Z., Zhou, C., Zhou, J., Zhou, X., Zhu, T., 2023. Qwen Technical Report. ArXiv Prepr. ArXiv230916609."},{"key":"10.1016\/j.ajp.2025.104707_bib3","series-title":"BELLE: be Everyone\u2019s large language model engine","author":"BELLEGroup","year":"2023"},{"key":"10.1016\/j.ajp.2025.104707_bib4","doi-asserted-by":"crossref","DOI":"10.2196\/68486","article-title":"Virtual patients using large language models: scalable, contextualized simulation of clinician-patient dialogue with feedback","volume":"27","author":"Cook","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.ajp.2025.104707_bib5","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1016\/j.cpr.2010.06.001","article-title":"Self-reported versus clinician-rated symptoms of depression as outcome measures in psychotherapy research on depression: a meta-analysis","volume":"30","author":"Cuijpers","year":"2010","journal-title":"Clin. Psychol. Rev."},{"key":"10.1016\/j.ajp.2025.104707_bib6","doi-asserted-by":"crossref","DOI":"10.1192\/j.eurpsy.2020.87","article-title":"Trends in (not) using scales in major depression: a categorization and clinical orientation","volume":"63","author":"Demyttenaere","year":"2020","journal-title":"Eur. Psychiatry"},{"key":"10.1016\/j.ajp.2025.104707_bib7","doi-asserted-by":"crossref","DOI":"10.1016\/j.ebiom.2024.105401","article-title":"Enhancing early detection of cognitive decline in the elderly: a comparative study utilizing large language models in clinical notes","volume":"109","author":"Du","year":"2024","journal-title":"eBioMedicine"},{"key":"10.1016\/j.ajp.2025.104707_bib8","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1038\/s41746-020-00376-2","article-title":"Deep learning-enabled medical computer vision","volume":"4","author":"Esteva","year":"2021","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib9","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1136\/jnnp.23.1.56","article-title":"A rating scale for depression","volume":"23","author":"Hamilton","year":"1960","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"10.1016\/j.ajp.2025.104707_bib10","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1109\/TSE.2024.3519464","article-title":"look before you leap: an exploratory study of uncertainty analysis for large language models","volume":"51","author":"Huang","year":"2025","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.ajp.2025.104707_bib11","author":"Jiang","year":"2024","journal-title":"Refine Large Language Model Fine-tuning via Instruction Vector"},{"key":"10.1016\/j.ajp.2025.104707_bib12","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1038\/s41746-024-01181-x","article-title":"Large language models outperform mental and medical health care professionals in identifying obsessive-compulsive disorder","volume":"7","author":"Kim","year":"2024","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib13","doi-asserted-by":"crossref","unstructured":"Kiyomaru, H., Sugiura, I., Kawahara, D., Kurohashi, S., 2024. A Comprehensive Analysis of Memorization in Large Language Models, in: Mahamood, S., Minh, N.L., Ippolito, D. (Eds.), Proceedings of the 17th International Natural Language Generation Conference. Association for Computational Linguistics, Tokyo, Japan, pp. 584\u2013596.","DOI":"10.18653\/v1\/2024.inlg-main.45"},{"key":"10.1016\/j.ajp.2025.104707_bib14","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1046\/j.1525-1497.2001.016009606.x","article-title":"The PHQ-9: validity of a brief depression severity measure","volume":"16","author":"Kroenke","year":"2001","journal-title":"J. Gen. Intern. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib15","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/s12650-024-00980-4","article-title":"C5: toward better conversation comprehension and contextual continuity for ChatGPT","volume":"27","author":"Liang","year":"2024","journal-title":"J. Vis."},{"key":"10.1016\/j.ajp.2025.104707_bib16","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1038\/s41746-024-01388-y","article-title":"Systematic review and meta-analysis of adverse events in clinical trials of mental health apps","volume":"7","author":"Linardon","year":"2024","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib17","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.genhosppsych.2020.11.016","article-title":"Discrepancies between self-rated depression and observed depression severity: the effects of personality and dysfunctional attitudes","volume":"70","author":"Ma","year":"2021","journal-title":"Gen. Hosp. Psychiatry"},{"key":"10.1016\/j.ajp.2025.104707_bib18","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyt.2021.747139","article-title":"The patient health Questionnaire-9 vs. The hamilton rating scale for depression in assessing major depressive disorder","volume":"12","author":"Ma","year":"2021","journal-title":"Front. Psychiatry"},{"key":"10.1016\/j.ajp.2025.104707_bib19","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.jad.2025.04.014","article-title":"Estimating depression severity in narrative clinical notes using large language models","volume":"381","author":"McCoy","year":"2025","journal-title":"J. Affect. Disord."},{"key":"10.1016\/j.ajp.2025.104707_bib20","doi-asserted-by":"crossref","first-page":"2734","DOI":"10.1002\/sim.7679","article-title":"Performance of intraclass correlation coefficient (ICC) as a reliability index under various distributions in scale reliability studies","volume":"37","author":"Mehta","year":"2018","journal-title":"Stat. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib21","doi-asserted-by":"crossref","first-page":"149","DOI":"10.14245\/ns.2347052.526","article-title":"Use of ChatGPT for determining clinical and surgical treatment of lumbar disc herniation with radiculopathy: a north American spine society guideline comparison","volume":"21","author":"Mejia","year":"2024","journal-title":"Neurospine"},{"key":"10.1016\/j.ajp.2025.104707_bib22","doi-asserted-by":"crossref","DOI":"10.2196\/10148","article-title":"Towards an artificially empathic conversational agent for mental health applications: system design and user perceptions","volume":"20","author":"Morris","year":"2018","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.ajp.2025.104707_bib23","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1037\/0022-006X.51.2.318","article-title":"Hamilton rating scale for depression: reliability and validity of judgments of novice raters","volume":"51","author":"O\u2019Hara","year":"1983","journal-title":"J. Consult. Clin. Psychol."},{"key":"10.1016\/j.ajp.2025.104707_bib24","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1038\/s43856-025-01021-3","article-title":"Multi-model assurance analysis showing large language models are highly vulnerable to adversarial hallucination attacks during clinical decision support","volume":"5","author":"Omar","year":"2025","journal-title":"Commun. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib25","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/s41746-023-00958-w","article-title":"A study of generative large language model for medical research and healthcare","volume":"6","author":"Peng","year":"2023","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib26","doi-asserted-by":"crossref","DOI":"10.3390\/jcm13113041","article-title":"Clinical and surgical applications of large language models: a systematic review","volume":"13","author":"Pressman","year":"2024","journal-title":"J. Clin. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib27","unstructured":"rany2, 2025. rany2\/edge-tts."},{"key":"10.1016\/j.ajp.2025.104707_bib28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1146\/annurev.clinpsy.3.022806.091415","article-title":"Ecological momentary assessment","volume":"4","author":"Shiffman","year":"2008","journal-title":"Annu. Rev. Clin. Psychol."},{"key":"10.1016\/j.ajp.2025.104707_bib29","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1002\/npr2.12404","article-title":"Machine learning algorithm-based estimation model for the severity of depression assessed using Montgomery-Asberg depression rating scale","volume":"44","author":"Shimamoto","year":"2024","journal-title":"Neuropsychopharmacol. Rep."},{"key":"10.1016\/j.ajp.2025.104707_bib30","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0267995","article-title":"Precise language responses versus easy rating scales\u2014Comparing respondents\u2019 views with clinicians\u2019 belief of the respondent\u2019s views","volume":"18","author":"Sikstr\u00f6m","year":"2023","journal-title":"PLOS ONE"},{"key":"10.1016\/j.ajp.2025.104707_bib31","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib32","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.103002","article-title":"Efficiency at scale: investigating the performance of diminutive language models in clinical tasks","volume":"157","author":"Taylor","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.ajp.2025.104707_bib33","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2025.104793","article-title":"MedicalGLM: a pediatric medical question answering model with a quality evaluation mechanism","volume":"165","author":"Wang","year":"2025","journal-title":"J. Biomed. Inf."},{"key":"10.1016\/j.ajp.2025.104707_bib34","article-title":"Chart review of patients receiving valsartan\u2013amlodipine single-pill combination versus valsartan and amlodipine combination for blood pressure goal achievement and effects on the hamilton anxiety rating\/hamilton depression rating scales","volume":"98","author":"Yin","year":"2019","journal-title":"Med. (Baltim. )"},{"key":"10.1016\/j.ajp.2025.104707_bib35","author":"Zhang","year":"2024","journal-title":"A Survey on the Memory Mechanism of Large Language Model based Agents"}],"container-title":["Asian Journal of Psychiatry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1876201825003508?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1876201825003508?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T16:06:51Z","timestamp":1773158811000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1876201825003508"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":35,"alternative-id":["S1876201825003508"],"URL":"https:\/\/doi.org\/10.1016\/j.ajp.2025.104707","relation":{},"ISSN":["1876-2018"],"issn-type":[{"value":"1876-2018","type":"print"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Can AI replace clinician-rated depression scales? The psychometric properties of HAMLET \u2013 Hamilton Large-Language-Model Evaluation Tool","name":"articletitle","label":"Article Title"},{"value":"Asian Journal of Psychiatry","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ajp.2025.104707","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104707"}}