A Clinician’s Guide to Running Custom Machine-Learning Models in an Electronic Health Record Environment

• Published in: Mayo Clinic proceedings Vol. 98; no. 3; pp. 445 - 450
• Main Authors: Ryu, Alexander J., Ayanian, Shant, Qian, Ray, Core, Marcia A., Heaton, Heather A., Lamb, Matthew W., Parikh, Riddhi S., Boyum, Jens P., Garza, Esteban L., Condon, Jennifer L., Peters, Steve G.
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01-03-2023; Elsevier, Inc
• Subjects: Analysis; Electronic Health Records; Electronic records; Emergency Service, Hospital; Health care industry; Health Facilities; Humans; Machine Learning; Management; Medical records; Running; Technology application; United States; UI; AI; IT; EHR; AUC; ED; ML
• DOI: 10.1016/j.mayocp.2022.11.019
• EISSN: 1942-5546
• ISSN: 0025-6196

We recently brought an internally developed machine-learning model for predicting which patients in the emergency department would require hospital admission into the live electronic health record environment. Doing so involved navigating several engineering challenges that required the expertise of multiple parties across our institution. Our team of physician data scientists developed, validated, and implemented the model. We recognize a broad interest and need to adopt machine-learning models into clinical practice and seek to share our experience to enable other clinician-led initiatives. This Brief Report covers the entire model deployment process, starting once a team has trained and validated a model they wish to deploy in live clinical operations.