Enhancing cause of death prediction: development and validation of machine learning models using multimodal data across multiple health-care sites
Machine learning models combining structured and unstructured EHR data accurately predict CoD within institutions but perform poorly across sites. Health-care institutions may benefit from adopting robust processes for locally tailored models, and future research should focus on enhancing model generalizability while addressing unique institutional data environments.
Authors
- D. Park
- Rishi Desai (ORCID: https://orcid.org/0000-0003-0299-7273)
- Candace C. Fuller (ORCID: https://orcid.org/0000-0002-8902-1435)
- Dax Westerman (ORCID: https://orcid.org/0000-0002-9547-7789)
- Ruth Reeves (ORCID: https://orcid.org/0000-0003-4260-2707)
- Melissa L McPheeters (ORCID: https://orcid.org/0000-0002-4423-797X)
- José J. Hernández‐Muñoz (ORCID: https://orcid.org/0000-0002-2553-3159)
- Judith C. Maro (ORCID: https://orcid.org/0000-0001-9900-2142)
- Michael F McLemore
- Haritha S. Pillai
- Jill M Whitaker
- Aida Kuzucan (ORCID: https://orcid.org/0000-0003-0893-7028)
- Kevin Coughlin
- Shirley V Wang
- Michele LeNoue-Newton
- Kerry Ngan
- Jessica A Buckner
- Mohammed Al-Garadi
- Michael E Matheny
- Joshua Lin Kueiyu
Institutions
- Brigham and Women's Hospital (US)
- Center for Drug Evaluation and Research (US)
- RTI International (US)
- Massachusetts General Hospital (US)
- VA Tennessee Valley Healthcare System (US)
- Harvard Pilgrim Health Care (US)
- Vanderbilt University Medical Center (US)
Publication Details
- Journal
- JAMIA Open
- Published
- 2025-12-12
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf175
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00