Enhancing patient representation learning with inferred family pedigrees improves disease risk prediction
Overall, our results highlight that family relations should not be overlooked in EHR research and illustrate ALIGATEHR's great potential for enhancing patient representation learning for predictive and interpretable modeling of EHRs.
Authors
- Nathan Lawless (ORCID: https://orcid.org/0000-0002-3120-1126)
- Jatin Arora (ORCID: https://orcid.org/0000-0001-9202-1906)
- Jan M. Kriegl
- Pierre Khoueiry (ORCID: https://orcid.org/0000-0001-7643-3310)
- Jatin Arora (ORCID: https://orcid.org/0000-0002-7754-9566)
- Zuoheng Wang (ORCID: https://orcid.org/0000-0002-7251-3687)
- James J. Cai (ORCID: https://orcid.org/0000-0002-8081-6725)
- Jan Jensen (ORCID: https://orcid.org/0000-0003-0657-4032)
- Johann de Jong (ORCID: https://orcid.org/0000-0002-2097-0915)
- Daniel Lam (ORCID: https://orcid.org/0000-0002-6536-5575)
- Hongyu Zhao (ORCID: https://orcid.org/0000-0003-1195-9607)
- A. Mesut Erzurumluoglu (ORCID: https://orcid.org/0000-0003-1322-8138)
- Xiayuan Huang (ORCID: https://orcid.org/0000-0002-3730-5014)
- Zhihao Ding (ORCID: https://orcid.org/0009-0003-2303-5599)
- Stephen A. Stanhope
Institutions
- Yale University (US)
- Digital Science (United States) (US)
- Boehringer Ingelheim (Australia) (AU)
- Boehringer Ingelheim (United States) (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2024-12-26
- DOI
- https://doi.org/10.1093/jamia/ocae297
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.69
Funders
- Yale University