{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T22:37:32Z","timestamp":1792708652913,"version":"4.5.0"},"reference-count":56,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Large language models (LLMs) are increasingly used to generate and evaluate patient-facing medical materials. Through persona prompting, LLMs can be instructed to simulate responses from individuals with different demographic and experiential backgrounds, offering a scalable approach for approximating patient feedback. However, it remains unclear how closely these simulated persona-based responses reflect real patient perspectives, and whether this alignment is consistent across demographic subgroups.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study assessed whether contemporary LLMs can simulate diverse patient perspectives on hospital discharge summaries when prompted with personas defined by education, gender, and health care use. We further examined whether persona-based simulation performance was equitable across subgroups by comparing LLM-generated responses with responses from a general-population human cohort under a standardized evaluation framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We evaluated 4 contemporary LLMs, GPT-4.1, GPT-5.2, Claude Sonnet 4.5, and Opus 4.6, against responses from 99 participants recruited through Prolific (Prolific Academic Ltd). Participants answered 10 questions for discharge summaries that varied in length and medical complexity. Questions included information-based items assessing factual comprehension and perception-based items assessing subjective understanding. Model-human alignment was measured using modal mean absolute error and expected absolute ordinal distance. We also conducted a chain-of-thought sensitivity analysis for cases with the greatest divergence between LLM-generated persona and matched human responses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across LLMs, persona responses aligned more closely with human responses on information-based items than on perception-based items. Education was the most consistent stratification axis: every model aligned more closely with the high-education subgroup than with the low-education subgroup on information items, suggesting that LLMs capture broad factual-comprehension differences associated with educational background. Perception items, in which subjective understanding and uncertainty dominate human responses, were simulated less reliably. Alignment also depended on discharge summary characteristics, with short but clinically complex summaries producing the largest divergence. Gender-related differences were smaller and inconsistent in direction, reflecting item-level modal flips rather than systematic distributional bias. Chain-of-thought improved alignment on some factual items but did not recover the full range of less common human responses. Across models, LLMs underselected \u201cI don\u2019t know\u201d and \u201cNot provided\u201d responses relative to humans, indicating a tendency to commit to determinate answers even when human participants expressed uncertainty.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Contemporary LLMs can approximate common response patterns within demographic subgroups, particularly for factual comprehension and education-based personas. However, they are less reliable for capturing heterogeneous and perception-based patient responses. Equity performance varied substantially across models, making model selection an important design consideration. Persona-based LLM simulation should be used as an assistive screening tool for patient materials and should complement, not replace, human evaluation with subgroup validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/89003","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:20:06Z","timestamp":1781612406000},"page":"e89003-e89003","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models\u2019 Simulation of Patient Comprehension of Discharge Summaries: Multimodel Evaluation Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4760-6072","authenticated-orcid":false,"given":"Xinyao","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8059-6718","authenticated-orcid":false,"given":"Rui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7620-4142","authenticated-orcid":false,"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5524-7450","authenticated-orcid":false,"given":"Jingwei","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6036-1516","authenticated-orcid":false,"given":"Qingyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8731-7884","authenticated-orcid":false,"given":"L Jean","family":"Camp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8963-8155","authenticated-orcid":false,"given":"Haixu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,10,22]]},"reference":[{"key":"R1","unstructured":"Achiam J Adler S Agarwal S et al. GPT-4 technical report. arXiv. Preprint posted online on Mar 4, 2023. [doi: 10.48550\/arXiv.2303.08774]"},{"key":"R2","volume":"24","author":"Chowdhery","journal-title":"J Mach Learn Res"},{"key":"R3","unstructured":"Thoppilan R De Freitas D Hall J et al. LaMDA: language models for dialog applications. arXiv. Preprint posted online on Feb 10, 2022. [doi: 10.48550\/arXiv.2201.08239]"},{"key":"R4","unstructured":"Brown T Mann B Ryder N et al. Language models are few-shot learners. Presented at: Advances in Neural Information Processing Systems 33; Dec 6-12, 2020:1877-1901; URL: https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3495724.3495883 [Accessed 18-10-2026]"},{"key":"R5","doi-asserted-by":"crossref","unstructured":"Salewski L Alaniz S Rio-Torto I Schulz E Akata Z . In-context impersonation reveals large language models\u2019 strengths and biases. Presented at: Advances in Neural Information Processing Systems 36; Dec 10-16, 2023:72044-72057; New Orleans, Louisiana, USA. 2023.URL: http:\/\/www.proceedings.com\/75280.html [Accessed 15-08-2026] [doi: 10.52202\/075280-3152]","DOI":"10.52202\/075280-3152"},{"key":"R6","doi-asserted-by":"crossref","unstructured":"Wu N Gong M Shou L Liang S Jiang D . Large language models are diverse role-players for summarization evaluation. Presented at: CCF International Conference on Natural Language Processing and Chinese Computing; Oct 12-15, 2023:695-707; Foshan, China. 2023.URL: https:\/\/dl.acm.org\/doi\/abs\/10.1007\/978-3-031-44693-1_54 [Accessed 18-10-2026] [doi: 10.1007\/978-3-031-44693-1_54]","DOI":"10.1007\/978-3-031-44693-1_54"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.2196\/50150","article-title":"A comparison of ChatGPT and fine-tuned Open Pre-Trained Transformers (OPT) against widely used sentiment analysis tools: sentiment analysis of COVID-19 survey data","volume":"11","author":"Lossio-Ventura","journal-title":"JMIR Ment Health"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1177\/106286069901400403","article-title":"What is necessary for high-quality discharge summaries?","volume":"14","author":"van Walraven","journal-title":"Am J Med Qual"},{"issue":"5","key":"R9","doi-asserted-by":"publisher","first-page":"281","DOI":"10.3390\/info11050281","article-title":"Machine learning based sentiment text classification for evaluating treatment quality of discharge summary","volume":"11","author":"Waheeb","journal-title":"Information"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Chintalapati A Agarwal S Senapati A Misbah M S NR Kumar S . Textual alchemy: transmuting BERT summaries with GAN elegance. Presented at: 2023 International Conference on Next Generation Electronics (NEleX); Dec 14-16, 2023:1-7; Vellore, India. 2023.URL: https:\/\/ieeexplore.ieee.org\/document\/10420998 [Accessed 18-10-2026] [doi: 10.1109\/NEleX59773.2023.10420998]","DOI":"10.1109\/NEleX59773.2023.10420998"},{"key":"R11","unstructured":"Jung H Kim Y Choi H et al. Enhancing clinical efficiency through LLM: discharge note generation for cardiac patients. arXiv. Preprint posted online on Apr 8, 2024. [doi: 10.48550\/arXiv.2404.05144]"},{"issue":"3","key":"R12","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.3201","article-title":"Artificial intelligence-generated draft replies to patient inbox messages","volume":"7","author":"Garcia","journal-title":"JAMA Netw Open"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Jones E Steinhardt J . Capturing failures of large language models via human cognitive biases. Presented at: Advances in Neural Information Processing Systems 35; Nov 28 to Dec 9, 2022:11785-11799; New Orleans, Louisiana, USA. URL: http:\/\/www.proceedings.com\/68431.html [Accessed 18-10-2026] [doi: 10.52202\/068431-0856]","DOI":"10.52202\/068431-0856"},{"issue":"6334","key":"R14","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1126\/science.aal4230","article-title":"Semantics derived automatically from language corpora contain human-like biases","volume":"356","author":"Caliskan","journal-title":"Science"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Bender EM Gebru T McMillan-Major A Shmitchell S . On the dangers of stochastic parrots: can language models be too big. Presented at: FAccT \u201921: 2021 ACM Conference on Fairness, Accountability, and Transparency; Mar 3-10, 2021:610-623; 2021.URL: https:\/\/dl.acm.org\/doi\/10.1145\/3442188.3445922 [Accessed 18-10-2026] [doi: 10.1145\/3442188.3445922]","DOI":"10.1145\/3442188.3445922"},{"key":"R16","doi-asserted-by":"crossref","unstructured":"Abid A Farooqi M Zou J . Persistent anti-muslim bias in large language models. Presented at: AIES \u201921: Proceedings of the 2021 AAAI\/ACM Conference on AI, Ethics, and Society; May 19-21, 2021:298-306; URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3461702 [Accessed 15-08-2026] [doi: 10.1145\/3461702.3462624]","DOI":"10.1145\/3461702.3462624"},{"key":"R17","unstructured":"Coda-Forno J Witte K Jagadish AK Binz M Akata Z Schulz E . Inducing anxiety in large language models increases exploration and bias. arXiv. Preprint posted online on Oct 15, 2024. [doi: 10.48550\/arXiv.2304.11111]"},{"key":"R18","doi-asserted-by":"crossref","unstructured":"Deshpande A Murahari V Rajpurohit T Kalyan A Narasimhan K . Toxicity in chatgpt: analyzing persona-assigned language models. Presented at: Findings of the Association for Computational Linguistics; Dec 6-10, 2023; Singapore. URL: https:\/\/aclanthology.org\/2023.findings-emnlp [Accessed 18-10-2026] [doi: 10.18653\/v1\/2023.findings-emnlp.88]","DOI":"10.18653\/v1\/2023.findings-emnlp.88"},{"issue":"6","key":"R19","doi-asserted-by":"publisher","first-page":"e428","DOI":"10.1016\/S2589-7500(24)00061-X","article-title":"Ethical and regulatory challenges of large language models in medicine","volume":"6","author":"Ong","journal-title":"Lancet Digit Health"},{"key":"R20","doi-asserted-by":"crossref","unstructured":"Elbattah M Arnaud E Ghazali DA Dequen G . Exploring the ethical challenges of large language models in emergency medicine: a comparative international review. Presented at: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Dec 3-5, 2024:5750-5755; Lisbon, Portugal. 2024.[doi: 10.1109\/BIBM62325.2024.10822376]","DOI":"10.1109\/BIBM62325.2024.10822376"},{"issue":"7","key":"R21","doi-asserted-by":"publisher","DOI":"10.1056\/AIra2400038","article-title":"Medical ethics of large language models in medicine","volume":"1","author":"Ong","journal-title":"NEJM AI"},{"key":"R22","doi-asserted-by":"crossref","unstructured":"Lampinen A Dasgupta I Chan S et al. Can language models learn from explanations in context? In: Findings of the Association for Computational Linguistics. Association for Computational Linguistics; 2022:537. [doi: 10.18653\/v1\/2022.findings-emnlp.38]","DOI":"10.18653\/v1\/2022.findings-emnlp.38"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Wei J Wang X Schuurmans D et al. Chain-of-thought prompting elicits reasoning in large language models. Presented at: Conference on Neural Information Processing Systems (NeurIPS 2022); Nov 28 to Dec 9, 2022:24824-24837; New Orleans, Louisiana, USA. 2022.URL: http:\/\/www.proceedings.com\/68431.html [Accessed 18-10-2026] [doi: 10.52202\/068431-1800]","DOI":"10.52202\/068431-1800"},{"key":"R24","unstructured":"Arora S Narayan A Chen MF et al. Ask me anything: a simple strategy for prompting language models. arXiv. Preprint posted online on Nov 20, 2022. [doi: 10.48550\/arXiv.2210.02441]"},{"key":"R25","unstructured":"Zhou Y Muresanu AI Han Z et al. Large language models are human-level prompt engineers. arXiv. Preprint posted online on Mar 10, 2023. [doi: 10.48550\/arXiv.2211.01910]"},{"key":"R26","unstructured":"Yuan Z Yuan H Tan C Wang W Huang S . How well do large language models perform in arithmetic tasks. arXiv. Preprint posted online on Mar 16, 2024. [doi: 10.48550\/arXiv.2304.02015]"},{"key":"R27","unstructured":"K\u0131c\u0131man E Ness R Sharma A Tan C . Causal reasoning and large language models: opening a new frontier for causality. arXiv. Preprint posted online on Aug 20, 2024. [doi: 10.48550\/arXiv.2305.00050]"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Han S Kim B Yoo JY et al. Meet your favorite character: open-domain chatbot mimicking fictional characters with only a few utterances. Presented at: 2022 Conference of the North American Chapter of the Association for Computational Linguistics; Jul 10-15, 2022:5114-5132; Seattle, United States. URL: https:\/\/aclanthology.org\/2022.naacl-main [Accessed 15-08-2026] [doi: 10.18653\/v1\/2022.naacl-main.377]","DOI":"10.18653\/v1\/2022.naacl-main.377"},{"key":"R29","unstructured":"Keskar NS McCann B Varshney LR Xiong C Socher R . CTRL: a conditional transformer language model for controllable generation. arXiv. Preprint posted online on Sep 20, 2019. [doi: 10.48550\/arxiv.1909.05858]"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Reynolds L McDonell K . Prompt programming for large language models: beyond the few-shot paradigm. Presented at: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems; May 8-13, 2021:1-7; Yokohama, Japan. May 8, 2021.URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3411763 [Accessed 15-08-2026] [doi: 10.1145\/3411763.3451760]","DOI":"10.1145\/3411763.3451760"},{"key":"R31","doi-asserted-by":"crossref","unstructured":"Shin T Razeghi Y Logan IV RL Wallace E Singh S . AutoPrompt: eliciting knowledge from language models with automatically generated prompts. Presented at: 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP); Nov 16-20, 2020:4222-4235; URL: https:\/\/aclanthology.org\/2020.emnlp-main [Accessed 15-08-2026] [doi: 10.18653\/v1\/2020.emnlp-main.346]","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"issue":"7987","key":"R32","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-023-06647-8","article-title":"Role play with large language models","volume":"623","author":"Shanahan","journal-title":"Nature"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Lin S Hilton J Evans O . TruthfulQA: measuring how models mimic human falsehoods. Presented at: 60th Annual Meeting of the Association for Computational Linguistics (Volume 1); May 22-27, 2022:3214-3252; Dublin, Ireland. 2022.URL: https:\/\/aclanthology.org\/2022.acl-long [Accessed 15-08-2026] [doi: 10.18653\/v1\/2022.acl-long.229]","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.2196\/72984","article-title":"Large language model symptom identification from clinical text: multicenter study","volume":"27","author":"McMurry","journal-title":"J Med Internet Res"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.2196\/81271","article-title":"Large language model-based patient simulation to foster communication skills in health care professionals: user-centered development and usability study","volume":"11","author":"Elhilali","journal-title":"JMIR Med Educ"},{"key":"R36","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":"R37","unstructured":"Aher GV Arriaga RI Kalai AT . Using large language models to simulate multiple humans and replicate human subject studies. Presented at: 40th International Conference on Machine Learning; Jul 23-29, 2023:337-371; Honolulu, Hawaii, USA. 2023.URL: https:\/\/proceedings.mlr.press\/v202\/aher23a.html [Accessed 18-10-2026]"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","journal-title":"Sci Data"},{"key":"R39","doi-asserted-by":"crossref","unstructured":"Kumichev G Blinov P Kuzkina Y et al. MedSyn: LLM-based synthetic medical text generation framework. Presented at: Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track; Sep 8-12, 2024:215-230; Vilnius, Lithuania. URL: https:\/\/dl.acm.org\/doi\/10.1007\/978-3-031-70381-2_14 [Accessed 18-10-2026] [doi: 10.1007\/978-3-031-70381-2_14]","DOI":"10.1007\/978-3-031-70381-2_14"},{"key":"R40","doi-asserted-by":"crossref","unstructured":"Wu H Boulenger P Faure A et al. EPFL-MAKE at \u201cdischarge me!\u201d: an LLM system for automatically generating discharge summaries of clinical electronic health record. Presented at: 23rd Workshop on Biomedical Natural Language Processing; 696-711; Bangkok, Thailand. 2024.URL: https:\/\/aclanthology.org\/2024.bionlp-1 [Accessed 16-08-2026] [doi: 10.18653\/v1\/2024.bionlp-1.61]","DOI":"10.18653\/v1\/2024.bionlp-1.61"},{"key":"R41","unstructured":"Kalai AT Nachum O Vempala SS Zhang E . Why language models hallucinate. arXiv. Preprint posted online on Sep 4, 2025. [doi: 10.48550\/arXiv.2509.04664]"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","first-page":"e12","DOI":"10.1016\/S2589-7500(23)00225-X","article-title":"Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study","volume":"6","author":"Zack","journal-title":"Lancet Digit Health"},{"issue":"3","key":"R43","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1038\/s42256-025-00986-z","article-title":"Large language models that replace human participants can harmfully misportray and flatten identity groups","volume":"7","author":"Wang","journal-title":"Nat Mach Intell"},{"issue":"3","key":"R44","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1089\/jwh.2010.2469","article-title":"Inclusion, analysis, and reporting of sex and race\/ethnicity in clinical trials: have we made progress?","volume":"20","author":"Geller","journal-title":"J Womens Health (Larchmt)"},{"issue":"3","key":"R45","doi-asserted-by":"publisher","first-page":"238","DOI":"10.17499\/JSSER.79630","article-title":"Evaluating text complexity and Flesch-Kincaid grade level","volume":"8","author":"Solnyshkina","journal-title":"J Soc Stud Educ Res"},{"key":"R46","unstructured":"SMOG readability formula: your tool for clearer health communication. Harvard TH Chan School of Public Health. URL: https:\/\/hsph.harvard.edu\/research\/health-communication\/resources\/smog\/ [Accessed 15-08-2026]"},{"issue":"9","key":"R47","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","article-title":"Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly","volume":"41","author":"Xian","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"16","key":"R48","doi-asserted-by":"publisher","first-page":"10207","DOI":"10.1080\/10447318.2024.2431761","article-title":"Prompting AI art: an investigation into the creative skill of prompt engineering","volume":"41","author":"Oppenlaender","journal-title":"Int J Hum-Comput Interact"},{"key":"R49","unstructured":"Wolf Y Wies N Avnery O Schwartz R . Fundamental limitations of alignment in large language models. arXiv. Preprint posted online on Jun 3, 2024. [doi: 10.48550\/arXiv.2304.11082]"},{"issue":"5","key":"R50","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1177\/17456916231214460","article-title":"AI psychometrics: assessing the psychological profiles of large language models through psychometric inventories","volume":"19","author":"Pellert","journal-title":"Perspect Psychol Sci"},{"issue":"7","key":"R51","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1038\/s41591-023-02366-9","article-title":"AI-generated text may have a role in evidence-based medicine","volume":"29","author":"Peng","journal-title":"Nat Med"},{"issue":"1","key":"R52","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00819-6","article-title":"Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers","volume":"6","author":"Gao","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R53","doi-asserted-by":"publisher","DOI":"10.1056\/AIra2400380","article-title":"RAG in health care: a novel framework for improving communication and decision-making by addressing LLM limitations","volume":"2","author":"Ng","journal-title":"NEJM AI"},{"key":"R54","doi-asserted-by":"crossref","unstructured":"Balasuriya Mudiyanselage U Jayprakash B Lee K Kwon KH . Disaggregated health data in LLMs: evaluating data equity in the context of Asian American representation. Presented at: 2025 AAAI\/ACM Conference on AI, Ethics, and Society; Oct 20-22, 2025:292-303; Madrid, Spain. URL: https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/view\/36549 [Accessed 18-10-2026] [doi: 10.1609\/aies.v8i1.36549]","DOI":"10.1609\/aies.v8i1.36549"},{"issue":"6","key":"R55","doi-asserted-by":"publisher","DOI":"10.1056\/AIp2401167","article-title":"A call for disclosure when using AI for patient communications","volume":"2","author":"Millen","journal-title":"NEJM AI"},{"key":"R56","unstructured":"llm_patient_centric_communicate. GitHub. URL: https:\/\/github.com\/xinyao1108\/llm_patient_centric_communicate [Accessed 14-08-2026]"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T21:45:14Z","timestamp":1792705514000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e89003"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,22]]},"references-count":56,"URL":"https:\/\/doi.org\/10.2196\/89003","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,22]]},"article-number":"v28i4e89003"}}