{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T18:56:43Z","timestamp":1790967403415,"version":"4.1.0"},"reference-count":28,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Training mental health clinicians to conduct standardized clinical assessments is challenging due to a lack of scalable, realistic practice opportunities. Traditional methods often fail to prepare trainees for the variability and complexity of real-world patient interactions, potentially impacting data quality in clinical trials. This paper introduces a novel approach to address this training gap using large language model (LLM)\u2013based interview simulations.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop and validate a voice-enabled virtual patient simulation system as a proof of concept. We described the development of the system and evaluated whether it could generate virtual patients that (1) accurately adhered to predefined clinical profiles, (2) maintained a coherent and consistent narrative, and (3) produced dialogue that is perceived as realistic.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We implemented a system that used an LLM to simulate patients with specified symptom profiles, demographic backgrounds, and distinct communication styles. The system\u2019s performance was analyzed through a mixed methods evaluation, which included a formal assessment by 5 experienced clinical raters who conducted simulated structured Montgomery-\u00c5sberg Depression Rating Scale (MADRS) interviews with 4 virtual patient personae, scored them on the scale, and provided qualitative feedback on the system\u2019s clinical plausibility, narrative cohesion, and dialogue realism.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Across 20 interviews, the virtual patients demonstrated reasonable adherence to their configured clinical profiles, with human rater scores falling near their predefined score configurations. The mean item difference between MADRS rater scores and configured scores was 0.52 (SD 0.75); interrater reliability for the total score was 0.90 (95% CI 0.68\u20100.99). Expert raters consistently gave average ratings of \u201cagree\u201d to \u201cstrongly agree\u201d when asked to evaluate the qualitative realism and cohesion of the virtual patients.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n LLM-powered virtual patient simulations offered a promising, scalable tool for training clinicians in standardized clinical assessment. This pilot study provides initial evidence for the system\u2019s ability to produce clinically relevant practice scenarios with reasonable fidelity.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/89066","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T15:00:16Z","timestamp":1788274816000},"page":"e89066-e89066","source":"Crossref","is-referenced-by-count":0,"title":["Voice-Enabled Virtual Patients for Interactive Training in Standardized Clinical Assessment: Mixed Methods Pilot Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8624-4616","authenticated-orcid":false,"given":"Veronica","family":"Bossio Botero","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2801-9005","authenticated-orcid":false,"given":"Vijay","family":"Yadav","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7898-8928","authenticated-orcid":false,"given":"Jacob","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6983-7779","authenticated-orcid":false,"given":"Anzar","family":"Abbas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0398-803X","authenticated-orcid":false,"given":"Michelle","family":"Worthington","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2020.07.080","article-title":"An old but still burning problem: inter-rater reliability in clinical trials with antidepressant medication","volume":"276","author":"Berendsen","journal-title":"J Affect Disord"},{"issue":"3","key":"R2","doi-asserted-by":"publisher","first-page":"101","DOI":"10.18203\/2349-3259.ijct20173133","article-title":"The impact of rater training on clinical outcomes assessment data: a literature review","volume":"4","author":"Sadler","journal-title":"Int J Clin Trials"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1601116","article-title":"Is the use of standardized patients more effective than role-playing in medical education? A meta-analysis","volume":"12","author":"Xiao","journal-title":"Front Med (Lausanne)"},{"key":"R4","unstructured":"Brun S . Effectively managing rater training and consistency in CNS trials. Precision for Medicine. 2022. URL: https:\/\/www.precisionformedicine.com\/blog\/effectively-managing-rater-training-and-consistency-in-cns-trials\/ [Accessed 06-08-2025]"},{"issue":"Supplement 1","key":"R5","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1016\/S0924-9338(11)72389-6","article-title":"P02-88 - Quantifying rater drift on the HAM-D in a sample of standardized rater training events: implications for reliability and sample size calculations","volume":"26","author":"Rothman","journal-title":"Eur Psychiatry"},{"issue":"27","key":"R6","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000038813","article-title":"The impact of simulation-based training in medical education: a review","volume":"103","author":"Elendu","journal-title":"Medicine (Baltimore)"},{"issue":"25","key":"R7","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000029503","article-title":"A review on the evolution of simulation-based training to help build a safer future","volume":"101","author":"Bienstock","journal-title":"Medicine (Baltimore)"},{"issue":"7","key":"R8","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.42027","article-title":"Standardized patients in medical education: a review of the literature","volume":"15","author":"Flanagan","journal-title":"Cureus"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1017\/S1351324922000420","article-title":"A randomized prospective study of a hybrid rule- and data-driven virtual patient","volume":"30","author":"Stiff","journal-title":"Nat Lang Eng"},{"issue":"10","key":"R10","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.71224","article-title":"The evolution from standardized to virtual patients in medical education","volume":"16","author":"Hamilton","journal-title":"Cureus"},{"key":"R11","volume":"132","author":"Parsons","journal-title":"Stud Health Technol Inform"},{"issue":"10","key":"R12","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1097\/ACM.0b013e3181edfe13","article-title":"Computerized virtual patients in health professions education: a systematic review and meta-analysis","volume":"85","author":"Cook","journal-title":"Acad Med"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.2196\/19285","article-title":"Artificial intelligence education and tools for medical and health informatics students: systematic review","volume":"6","author":"Sapci","journal-title":"JMIR Med Educ"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.3389\/frvir.2024.1377210","article-title":"Towards believable and educational conversations with virtual patients","volume":"5","author":"Graf","journal-title":"Front Virtual Real"},{"key":"R15","doi-asserted-by":"publisher","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","journal-title":"J Med Internet Res"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.2196\/58623","article-title":"Integrating GPT-based AI into virtual patients to facilitate communication training among medical first responders: usability study of mixed reality simulation","volume":"8","author":"Guti\u00e9rrez Maquil\u00f3n","journal-title":"JMIR Form Res"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Wang R Milani S Chiu JC et al. PATIENT-\u03c8: using large language models to simulate patients for training mental health professionals. arXiv. Preprint posted online on May 30, 2024. [doi: 10.48550\/arXiv.2405.19660]","DOI":"10.18653\/v1\/2024.emnlp-main.711"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.2196\/68056","article-title":"Leveraging large language models for simulated psychotherapy client interactions: development and usability study of Client101","volume":"11","author":"Cabrera Lozoya","journal-title":"JMIR Med Educ"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.2196\/63353","article-title":"Assessing ChatGPT\u2019s capability as a new age standardized patient: qualitative study","volume":"11","author":"Cross","journal-title":"JMIR Med Educ"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.2196\/79091","article-title":"Embracing the future of medical education with large language model-based virtual patients: scoping review","volume":"27","author":"Zeng","journal-title":"J Med Internet Res"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.134.4.382","article-title":"A new depression scale designed to be sensitive to change","volume":"134","author":"Montgomery","journal-title":"Br J Psychiatry"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2019.05.077","article-title":"Consistency checks to improve measurement with the Montgomery-Asberg Depression Rating Scale (MADRS)","volume":"256","author":"Rabinowitz","journal-title":"J Affect Disord"},{"key":"R23","unstructured":"Claude 3.7 Sonnet and Claude Code. Anthropic. URL: https:\/\/www.anthropic.com\/news\/claude-3-7-sonnet [Accessed 14-09-2026]"},{"key":"R24","unstructured":"Amazon Transcribe. Amazon Web Services. URL: https:\/\/aws.amazon.com\/transcribe\/ [Accessed 14-09-2026]"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3154776","article-title":"Personas for artificial intelligence (AI) an open source toolbox","volume":"10","author":"Holzinger","journal-title":"IEEE Access"},{"key":"R26","unstructured":"ElevenLabs. URL: https:\/\/elevenlabs.io\/ [Accessed 14-09-2026]"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1192\/bjp.bp.106.032532","article-title":"Development and reliability of a structured interview guide for the Montgomery Asberg Depression Rating Scale (SIGMA)","volume":"192","author":"Williams","journal-title":"Br J Psychiatry"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109561","article-title":"Fine-tuning language model embeddings to reveal domain knowledge: an explainable artificial intelligence perspective on medical decision making","volume":"139","author":"Krai\u0161nikovi\u0107","journal-title":"Eng Appl Artif Intell"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T18:44:09Z","timestamp":1790966649000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e89066"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":28,"URL":"https:\/\/doi.org\/10.2196\/89066","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]},"article-number":"v28i3e89066"}}