Improving clinical decision support through interpretable machine learning and error handling in electronic health records
This work is the first to translate clinical domain knowledge into mathematical constraints, model cross-vital dependencies, and identify aberrations in high-dimensional medical data. Our method allows for error handling in EMR and confers interpretability and superior predictive power to models trained for clinical decision support.
Authors
- Rishikesan Kamaleswaran (ORCID: https://orcid.org/0000-0001-8366-4811)
- Hassan Mortagy
- Mehak Arora (ORCID: https://orcid.org/0000-0003-1225-9549)
- Philip Yang (ORCID: https://orcid.org/0000-0001-5142-1137)
- Swati Gupta (ORCID: https://orcid.org/0000-0002-9566-3856)
- Andre L. Holder (ORCID: https://orcid.org/0000-0003-2635-3923)
- Nathan Dwarshuis (ORCID: https://orcid.org/0009-0001-9615-0243)
- Jeffrey Wang (ORCID: https://orcid.org/0000-0002-6900-8268)
Institutions
- Georgia Institute of Technology (US)
- Emory University (US)
- Duke University (US)
- Massachusetts Institute of Technology (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-04-09
- DOI
- https://doi.org/10.1093/jamia/ocaf058
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- National Science Foundation