Large Language Model Agent for Drafting Structured Responses to Non-Urgent Patient Portal Messages Using Local Clinical Protocols, Physician-Approved Templates, Patient History, and Message Intent Classification

cirpublications.com-ST7J-1790880684-r981397343 1790880684 Clinical Intelligence Research Press info@cirpublications.com Clinical Intelligence Research Press Journal of Health Informatics and Digital Systems J. Health Inform. Digit. Syst. 3149-8973 2026 6 1 Large Language Model Agent for Drafting Structured Responses to Non-Urgent Patient Portal Messages Using Local Clinical Protocols, Physician-Approved Templates, Patient History, and Message Intent Classification Victor Hugo Daniel Cruz Javier Salazar 2026 10.68159/r981397343 https://cirpublications.com/pub/journal/2/article/r981397343 Liu S, McCoy AB, Wright AP, Carew B, Genkins JZ, Huang SS, et al. Leveraging large language models for generating responses to patient messages: A subjective analysis. J Am Med Inform Assoc. 2024;31(6):1367–79. Garcia P, Ma SP, Shah S, Smith M, Jeong Y, Devon-Sand A, et al. Artificial intelligence–generated draft replies to patient inbox messages. JAMA Netw Open. 2024;7(3):e243201. Tai-Seale M, Baxter SL, Vaida F, Walker A, Sitapati AM, Osborne C, et al. AI-generated draft replies integrated into health records and physicians' electronic communication. JAMA Netw Open. 2024;7(4):e246565. Baxter SL, Longhurst CA, Millen M, Sitapati AM, Tai-Seale M. Generative artificial intelligence responses to patient messages in the electronic health record: Early lessons learned. JAMIA Open. 2024;7(2):ooae028. Liu S, Wright AP, McCoy AB, Huang SS, Steitz B, Wright A. Detecting emergencies in patient portal messages using large language models and knowledge graph-based retrieval-augmented generation. J Am Med Inform Assoc. 2025;32(6):1032–9. Yang J, So J, Zhang H, Jones S, Connolly DM, Golding C, et al. Development and evaluation of an artificial intelligence-based workflow for the prioritization of patient portal messages. JAMIA Open. 2024;7(3):ooae078. Anderson BJ, Zia ul Haq M, Zhu Y, Hornback A, Cowan AD, Mott M, et al. Development and evaluation of a model to manage patient portal messages. NEJM AI. 2025;2(3):AIoa2400354. Nguyen D, Lee S, La K, Kellogg M, Synghal R, Anwar B, et al. Performance of an intelligent messaging tool for clinical communications. JAMA Netw Open. 2026;9(1):e2553174. Yan S, Knapp W, Leong A, Kadkhodazadeh S, Das S, Jones VG, et al. Prompt engineering on leveraging large language models in generating responses to InBasket messages. J Am Med Inform Assoc. 2024;31(10):2263–70. Chen S, Guevara M, Moningi S, Hoebers F, Elhalawani H, Kann BH, et al. The effect of using a large language model to respond to patient messages. Lancet Digit Health. 2024;6(6):e379–e381. Liu S, Wright AP, McCoy AB, Huang SS, Genkins JZ, Peterson JF, et al. Using large language models to guide patients to create efficient and comprehensive clinical care messages. J Am Med Inform Assoc. 2024;31(8):1665–70. Hong C, Chowdhury A, Sorrentino AD, Wang H, Agrawal M, Bedoya A, et al. Application of unified health large language model evaluation framework to In-Basket message replies: Bridging qualitative and quantitative assessments. J Am Med Inform Assoc. 2025;32(4):626–37. Bootsma-Robroeks CM, Workum JD, Schuit SC, Hoekman A, Mehri T, Doornberg JN, et al. AI-generated draft replies to patient messages: Exploring effects of implementation. Front Digit Health. 2025;7:1588143. Biro JM, Handley JL, Malcolm McCurry J, Visconti A, Weinfeld J, Trafton JG, et al. Opportunities and risks of artificial intelligence in patient portal messaging in primary care. NPJ Digit Med. 2025;8(1):222. Lee NS, Richards N, Grandominico J, Cronin RM, Hendricks AK, Tripathi RS, et al. Use of a medical communication framework to assess the quality of generative artificial intelligence replies to primary care patient portal messages: Content analysis. JMIR Form Res. 2025;9:e71966. Cronin RM, Fabbri D, Denny JC, Rosenbloom ST, Jackson GP. A comparison of rule-based and machine learning approaches for classifying patient portal messages. Int J Med Inform. 2017;105:110–20. Sulieman L, Gilmore D, French C, Cronin RM, Jackson GP, Russell M, et al. Classifying patient portal messages using convolutional neural networks. J Biomed Inform. 2017;74:59–70. Ren Y, Wu D, Khurana A, Mastorakos G, Fu S, Zong N, et al. Classification of patient portal messages with BERT-based language models. In: 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI). Piscataway (NJ): IEEE; 2023. p. 176–82. Ren Y, Wu Y, Fan JW, Khurana A, Fu S, Wu D, et al. Automatic uncovering of patient primary concerns in portal messages using a fusion framework of pretrained language models. J Am Med Inform Assoc. 2024;31(8):1714–24. Davoudi A, Lee NS, Luong T, Delaney T, Asch E, Chaiyachati K, et al. Identifying medication-related intents from a bidirectional text messaging platform for hypertension management using an unsupervised learning approach: Retrospective observational pilot study. J Med Internet Res. 2022;24(6):e36151. English E, Laughlin J, Sippel J, DeCamp M, Lin CT. Utility of artificial intelligence–generative draft replies to patient messages. JAMA Netw Open. 2024;7(10):e2438573. Kim J, Chen ML, Rezaei SJ, Liang AS, Seav SM, Onyeka S, et al. Perspectives on artificial intelligence–generated responses to patient messages. JAMA Netw Open. 2024;7(10):e2438535. Cavalier JS, Goldstein BA, Ravitsky V, Bélisle-Pipon JC, Bedoya A, Maddocks J, et al. Ethics in patient preferences for artificial intelligence–drafted responses to electronic messages. JAMA Netw Open. 2025;8(3):e250449. Liang AS, Vedak S, Dussaq A, Yao DH, Villarreal JA, Thomas S, et al. Artificial intelligence-generated draft replies to patient messages in pediatrics. JAMIA Open. 2025;8(6):ooaf159. Small WR, Wiesenfeld BM, Brandfield-Harvey B, Jonassen Z, Mandal S, Stevens ER, et al. Large language model–based responses to patients’ in-basket messages. JAMA Netw Open. 2024;7(7):e2422399. Mandal S, Wiesenfeld BM, Szerencsy AC, Small WR, Major V, Richardson S, et al. Utilization of generative AI-drafted responses for managing patient-provider communication. NPJ Digit Med. 2025;8(1):591. TaftiAhmad P. Probing patient messages enhanced by natural language processing: A top-down message corpus analysis. Health Data Sci. 2021. Chen J, Lalor J, Liu W, Druhl E, Granillo E, Vimalananda VG, et al. Detecting hypoglycemia incidents reported in patients’ secure messages: Using cost-sensitive learning and oversampling to reduce data imbalance. J Med Internet Res. 2019;21(3):e11990. Hu D, Guo Y, Zhou Y, Flores L, Zheng K. A systematic review of early evidence on generative AI for drafting responses to patient messages. NPJ Health Syst. 2025;2(1):27.