Greater value add from electronic health records than polygenic risk scores for predicting myocardial infarction in machine learning
PRSs provide limited standalone utility for MI prediction compared to detailed diagnostic data. Their clinical value likely lies in integration with EHR-based models. Future work should focus on multi-modal approaches that contextualize PRS information within broader clinical data.
Authors
- May D. Wang (ORCID: https://orcid.org/0000-0003-3961-3608)
- Andrew Hornback (ORCID: https://orcid.org/0009-0009-5461-5848)
- Monica Isgut (ORCID: https://orcid.org/0000-0001-9171-8138)
- Anthony Chang (ORCID: https://orcid.org/0000-0001-6694-1880)
- Shriprasad R. Deshpande (ORCID: https://orcid.org/0000-0002-8358-9783)
- Youwen Sun (ORCID: https://orcid.org/0000-0002-9934-1328)
- Han Bao (ORCID: https://orcid.org/0009-0002-2149-6239)
- Blake Anderson (ORCID: https://orcid.org/0000-0002-4956-6721)
- Katherine Choi
Institutions
- Children's Hospital of Orange County (US)
- Georgia Institute of Technology (US)
- Children's National (US)
- Emory University (US)
Publication Details
- Journal
- Communications Medicine
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1038/s43856-025-01138-5
- Citations
- 3
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 7.44
Funders
- Microsoft Research
- Parker H. Petit Institute for Bioengineering and Bioscience