{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:28:27Z","timestamp":1777422507747,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K01MH137386"],"award-info":[{"award-number":["K01MH137386"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K24AR075060"],"award-info":[{"award-number":["K24AR075060"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Patients with diabetes are at increased risk of comorbid depression or anxiety, complicating their management. This study evaluated the performance of large language models (LLMs) in detecting these symptoms from secure patient messages. We applied multiple approaches, including engineered prompts, systemic persona, temperature adjustments, and zero-shot and few-shot learning, to identify the best-performing model and enhance performance. Three out of five LLMs demonstrated excellent performance (over 90% of F-1 and accuracy), with Llama 3.1 405B achieving 93% in both F-1 and accuracy using a zero-shot approach. While LLMs showed promise in binary classification and handling complex metrics like Patient Health Questionnaire-4, inconsistencies in challenging cases warrant further real-life assessment. The findings highlight the potential of LLMs to assist in timely screening and referrals, providing valuable empirical knowledge for real-world triage systems that could improve mental health care for patients with chronic diseases.<\/jats:p>","DOI":"10.1038\/s41746-025-01969-5","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:21:12Z","timestamp":1759234872000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Optimizing large language models for detecting symptoms of depression\/anxiety in chronic diseases patient communications"],"prefix":"10.1038","volume":"8","author":[{"given":"Jiyeong","family":"Kim","sequence":"first","affiliation":[]},{"given":"Stephen P.","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Michael L.","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Isaac R.","family":"Galatzer-Levy","sequence":"additional","affiliation":[]},{"given":"John","family":"Torous","sequence":"additional","affiliation":[]},{"given":"Peter J.","family":"van Roessel","sequence":"additional","affiliation":[]},{"given":"Christopher","family":"Sharp","sequence":"additional","affiliation":[]},{"given":"Michael A.","family":"Pfeffer","sequence":"additional","affiliation":[]},{"given":"Carolyn I.","family":"Rodriguez","sequence":"additional","affiliation":[]},{"given":"Eleni","family":"Linos","sequence":"additional","affiliation":[]},{"given":"Jonathan H.","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"1969_CR1","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.ijcard.2007.05.020","volume":"125","author":"C Norra","year":"2008","unstructured":"Norra, C., Skobel, E. C., Arndt, M. & Schauerte, P. High impact of depression in heart failure: Early diagnosis and treatment options. Int. J. Cardiol. 125, 220\u2013231 (2008).","journal-title":"Int. J. Cardiol."},{"key":"1969_CR2","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.ijcard.2022.05.056","volume":"364","author":"CA Pivato","year":"2022","unstructured":"Pivato, C. A. et al. Depression and ischemic heart disease. Int J. Cardiol. 364, 9\u201315 (2022).","journal-title":"Int J. Cardiol."},{"key":"1969_CR3","doi-asserted-by":"publisher","unstructured":"Khaledi M., Haghighatdoost F., Feizi A., Aminorroaya A. The prevalence of comorbid depression in patients with type 2 diabetes: an updated systematic review and meta-analysis on huge number of observational studies. Acta Diabetol. 56. https:\/\/doi.org\/10.1007\/S00592-019-01295-9 (2019).","DOI":"10.1007\/S00592-019-01295-9"},{"key":"1969_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41572-019-0135-7","volume":"6","author":"SM Gold","year":"2020","unstructured":"Gold, S. M. et al. Comorbid depression in medical diseases. Nat. Rev. Dis. Prim. 6, 1\u201322 (2020).","journal-title":"Nat. Rev. Dis. Prim."},{"key":"1969_CR5","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-016-1100-6","volume":"16","author":"KY Chen","year":"2016","unstructured":"Chen, K. Y., Evans, R. & Larkins, S. Why are hospital doctors not referring to Consultation-Liaison Psychiatry? - A systemic review. BMC Psychiatry 16, 390 (2016).","journal-title":"BMC Psychiatry"},{"key":"1969_CR6","unstructured":"Beck A. J., Page C., Buche J., Rittman D., Gaiser M. Estimating the Distribution of the U.S. Psychiatry Subspecialist Workforce Project Team\u2014Google Search. Accessed March 5, 2025. https:\/\/www.google.com\/search?sca_esv=e51cbab9ee5c3981&rlz=1C5GCCM_en&q=Beck+AJ,+Page+C,+Buche+J,+Rittman+D,+Gaiser+M.+Estimating+the+Distribution+of+the+U.S.+Psychiatry+Subspecialist+Wor+kforce+Project+Team&sa=X&ved=2ahUKEwjuppfLmPOLAxUsFzQIHbiQKF0Q7xYoAHoECAoQAQ&biw=1102&bih=912&dpr=2."},{"key":"1969_CR7","doi-asserted-by":"publisher","unstructured":"de Pinho L. G. et al. Patient-centered care for patients with depression or anxiety disorder: an integrative review. J. Pers. Med. 11. https:\/\/doi.org\/10.3390\/JPM11080776 (2021).","DOI":"10.3390\/JPM11080776"},{"key":"1969_CR8","doi-asserted-by":"publisher","first-page":"e43086","DOI":"10.2196\/43086","volume":"24","author":"MR Brands","year":"2022","unstructured":"Brands, M. R. et al. Patient-centered digital health records and their effects on health outcomes: systematic review. J. Med. Internet Res. 24, e43086 (2022).","journal-title":"J. Med. Internet Res."},{"key":"1969_CR9","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1136\/amiajnl-2012-001253","volume":"20","author":"AE Wade-Vuturo","year":"2013","unstructured":"Wade-Vuturo, A. E., Mayberry, L. S. & Osborn, C. Y. Secure messaging and diabetes management: experiences and perspectives of patient portal users. J. Am. Med Inf. Assoc. Jamia. 20, 519\u2013525 (2013).","journal-title":"J. Am. Med Inf. Assoc. Jamia."},{"key":"1969_CR10","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.122.028120","volume":"12","author":"A Sarraju","year":"2023","unstructured":"Sarraju, A. et al. Identifying reasons for statin nonuse in patients with diabetes using deep learning of electronic health records. J. Am. Heart Assoc. 12, e028120. https:\/\/doi.org\/10.1161\/JAHA.122.028120 (2023).","journal-title":"J. Am. Heart Assoc."},{"key":"1969_CR11","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1001\/jamapediatrics.2023.2373","volume":"177","author":"K Beam","year":"2023","unstructured":"Beam, K. et al. Performance of a large language model on practice questions for the neonatal board examination. JAMA Pediatr. 177, 977\u2013979 (2023).","journal-title":"JAMA Pediatr."},{"key":"1969_CR12","doi-asserted-by":"publisher","unstructured":"Cai Z. R. et al. Assessment of correctness, content omission, and risk of harm in large language model responses to dermatology continuing medical education questions. J. Investig. Dermatol. Published online February 2, 2024:S0022-202X(24)00088-5. https:\/\/doi.org\/10.1016\/j.jid.2024.01.015.","DOI":"10.1016\/j.jid.2024.01.015"},{"key":"1969_CR13","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1038\/s41746-024-01181-x","volume":"7","author":"J Kim","year":"2024","unstructured":"Kim, J. et al. Large language models outperform mental and medical health care professionals in identifying obsessive-compulsive disorder. NPJ Digit. Med. 7, 193 (2024).","journal-title":"NPJ Digit. Med."},{"key":"1969_CR14","doi-asserted-by":"publisher","first-page":"e53043","DOI":"10.2196\/53043","volume":"11","author":"Z Elyoseph","year":"2024","unstructured":"Elyoseph, Z. & Levkovich, I. Comparing the perspectives of generative AI, mental health experts, and the general public on schizophrenia recovery: case vignette study. JMIR Ment. Health 11, e53043 (2024).","journal-title":"JMIR Ment. Health"},{"key":"1969_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102988","volume":"157","author":"N Taylor","year":"2024","unstructured":"Taylor, N. et al. Model development for bespoke large language models for digital triage assistance in mental health care. Artif. Intell. Med. 157, 102988. https:\/\/doi.org\/10.1016\/j.artmed.2024.102988 (2024).","journal-title":"Artif. Intell. Med."},{"key":"1969_CR16","doi-asserted-by":"publisher","first-page":"e54617","DOI":"10.2196\/54617","volume":"26","author":"D Shin","year":"2024","unstructured":"Shin, D., Kim, H., Lee, S., Cho, Y. & Jung, W. Using large language models to detect depression from user-generated diary text data as a novel approach in digital mental health screening: instrument validation study. J. Med Internet Res. 26, e54617 (2024).","journal-title":"J. Med Internet Res."},{"key":"1969_CR17","doi-asserted-by":"publisher","DOI":"10.2174\/0117450179315688240607052117","volume":"20","author":"U Madububambachu","year":"2024","unstructured":"Madububambachu, U., Ukpebor, A. & Ihezue, U. Machine learning techniques to predict mental health diagnoses: a systematic literature review. Clin. Pr. Epidemiol. Ment. Health CP Emh. 20, e17450179315688. https:\/\/doi.org\/10.2174\/0117450179315688240607052117 (2024).","journal-title":"Clin. Pr. Epidemiol. Ment. Health CP Emh."},{"key":"1969_CR18","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1038\/s41746-024-01203-8","volume":"7","author":"J Guerreiro","year":"2024","unstructured":"Guerreiro, J. et al. Transatlantic transferability and replicability of machine-learning algorithms to predict mental health crises. NPJ Digit. Med. 7, 227 (2024).","journal-title":"NPJ Digit. Med."},{"key":"1969_CR19","unstructured":"Xu, X. et al. Leveraging Large Language Models for Mental Health Prediction via Online Text Data. (2023)."},{"key":"1969_CR20","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1056\/NEJMp2406135","volume":"391","author":"SS Jain","year":"2024","unstructured":"Jain, S. S., Mello, M. M. & Shah, N. H. Avoiding financial toxicity for patients from clinicians\u2019 use of AI. N. Engl. J. Med. 391, 1171\u20131173 (2024).","journal-title":"N. Engl. J. Med."},{"key":"1969_CR21","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.1038\/s41386-024-01841-2","volume":"49","author":"RH Perlis","year":"2024","unstructured":"Perlis, R. H., Goldberg, J. F., Ostacher, M. J. & Schneck, C. D. Clinical decision support for bipolar depression using large language models. Neuropsychopharmacol. Publ. Am. Coll. Neuropsychopharmacol. 49, 1412\u20131416 (2024).","journal-title":"Neuropsychopharmacol. Publ. Am. Coll. Neuropsychopharmacol."},{"key":"1969_CR22","doi-asserted-by":"publisher","first-page":"e002391","DOI":"10.1136\/fmch-2023-002391","volume":"11","author":"I Levkovich","year":"2023","unstructured":"Levkovich, I. & Elyoseph, Z. Identifying depression and its determinants upon initiating treatment: ChatGPT versus primary care physicians. Fam. Med. Community Health 11, e002391 (2023).","journal-title":"Fam. Med. Community Health"},{"key":"1969_CR23","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1001\/jamainternmed.2024.0295","volume":"184","author":"S Cabral","year":"2024","unstructured":"Cabral, S. et al. Clinical reasoning of a generative artificial intelligence model compared with physicians. JAMA Intern. Med. 184, 581\u2013583 (2024).","journal-title":"JAMA Intern. Med."},{"key":"1969_CR24","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.clinbiochem.2023.01.002","volume":"113","author":"N Rabbani","year":"2023","unstructured":"Rabbani, N. et al. Targeting repetitive laboratory testing with electronic health records-embedded predictive decision support: a pre-implementation study. Clin. Biochem. 113, 70\u201377 (2023).","journal-title":"Clin. Biochem."},{"key":"1969_CR25","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","volume":"333","author":"S Bedi","year":"2025","unstructured":"Bedi, S. et al. Testing and evaluation of health care applications of large language models: a systematic review. JAMA 333, 319\u2013328 (2025).","journal-title":"JAMA"},{"key":"1969_CR26","doi-asserted-by":"publisher","unstructured":"Devlin J., Chang M. W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. Published online May 24, 2019. https:\/\/doi.org\/10.48550\/arXiv.1810.04805.","DOI":"10.48550\/arXiv.1810.04805"},{"key":"1969_CR27","doi-asserted-by":"publisher","unstructured":"Grootendorst M. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. Published online March 11, 2022. https:\/\/doi.org\/10.48550\/arXiv.2203.05794.","DOI":"10.48550\/arXiv.2203.05794"},{"key":"1969_CR28","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1093\/jamia\/ocaf005","volume":"32","author":"MY Ng","year":"2025","unstructured":"Ng, M. Y., Helzer, J., Pfeffer, M. A., Seto, T. & Hernandez-Boussard, T. Development of secure infrastructure for advancing generative artificial intelligence research in healthcare at an academic medical center. J. Am. Med. Inf. Assoc. 32, 586\u2013588 (2025).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"1969_CR29","unstructured":"An ultra-brief screening scale for anxiety and depression: the PHQ-4\u2014PubMed. Accessed March 1, 2025. https:\/\/pubmed.ncbi.nlm.nih.gov\/19996233\/."},{"key":"1969_CR30","doi-asserted-by":"publisher","first-page":"e5471","DOI":"10.1097\/GOX.0000000000005471","volume":"11","author":"T Leypold","year":"2023","unstructured":"Leypold, T., Sch\u00e4fer, B., Boos, A. & Beier, J. P. Can AI Think Like a Plastic Surgeon? Evaluating GPT-4\u2019s Clinical Judgment in Reconstructive Procedures of the Upper Extremity. Plast. Reconstr. Surg. Glob. Open. 11, e5471 (2023).","journal-title":"Plast. Reconstr. Surg. Glob. Open."},{"key":"1969_CR31","unstructured":"Kojima T., Gu S (Shane), Reid M., Matsuo Y., Iwasawa Y. Large Language Models are Zero-Shot Reasoners. Adv. Neural Inf. Process Syst. 2022;35:22199-22213. Accessed March 19, 2024. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/8bb0d291acd4acf06ef112099c16f326-Abstract-Conference.html."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01969-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01969-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01969-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:21:13Z","timestamp":1759234873000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01969-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1969"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01969-5","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,30]]},"assertion":[{"value":"8 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"In the last 3 years, C.I.R. has served as a consultant for Biohaven Pharmaceuticals, Osmind, and Biogen; and receives research grant support from Biohaven Pharmaceuticals, a stipend from American Psychiatric Association Publishing for her role as Deputy Editor at The American Journal of Psychiatry, and book royalties from American Psychiatric Association Publishing. The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"580"}}