Abstract
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.
Abbreviations and Acronyms:
AI (artificial intelligence), AUC (area under the receiver-operator curve), ED (emergency department), EHR (electronic health record), IT (information technology), ML (machine-learning), UI (user interface)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Mayo Clinic ProceedingsAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Hospital and emergency department crowding in the United States.Emerg Med. 2003; 15: 22-27https://doi.org/10.1046/J.1442-2026.2003.00403.X
- Emergency department crowding: the canary in the health care system.N Engl J Med Catalyst. 2021; 5https://doi.org/10.1056/CAT.21.0217
- Hospital capacity and operations in the coronavirus disease 2019 (COVID-19) pandemic: planning for the nth patient.JAMA Health Forum. 2020; 1e200345https://doi.org/10.1001/JAMAHEALTHFORUM.2020.0345
News and Publications. The Johns Hopkins Hospital launches capacity command center to enhance hospital operations. Johns Hopkins Medicine. Published online October 26, 2016. Accessed November 16, 2020. https://www.hopkinsmedicine.org/news/media/releases/the_johns_hopkins_hospital_launches_capacity_command_center_to_enhance_hospital_operations
- Improving patient-care with hospital command centers: AI/ machine learning insights medical technology.https://www.medtechimpact.com/improving-patient-care-with-hospital-command-centers/Date accessed: November 16, 2020
- Assessing the generalizability of a clinical machine learning model across multiple emergency departments.Mayo Clin Proc Innov Qual Outcomes. 2022; 6: 193-199https://doi.org/10.1016/J.MAYOCPIQO.2022.03.003/ATTACHMENT/52B19760-0F6C-418E-8227-8B6FEA4B2EB9/MMC1.PDF
Article info
Identification
Copyright
© 2022 Mayo Foundation for Medical Education and Research. Published by Elsevier Inc. All rights reserved.
ScienceDirect
Access this article on ScienceDirectLinked Article
- Implementing Machine Learning in the Electronic Health Record: Checklist of Essential ConsiderationsMayo Clinic ProceedingsVol. 98Issue 3
- PreviewMachine learning (ML) holds significant promise for improving clinical care.1 To facilitate their appropriate and effective use, it is important that clinical guidance based on these ML models is provided automatically to end users as a part of routine clinical care processes,2 in particular through integration with electronic health record (EHR) systems. However, there is still relatively little literature on the actual deployment of ML models in EHRs to facilitate their appropriate use.
- Full-Text
- Preview
