Enhancing patient representation learning from electronic health records through predicted family relations
Authors:
- Xiayuan HuangXHXiayuan Huang
- Abdullah Mesut ErzurumluogluAEAbdullah Mesut Erzurumluoglu
- Zuoheng WangZWZuoheng Wang
- Johann de JongJJJohann de Jong
Preprint
Abstract
Artificial intelligence and machine learning are powerful tools in analyzing electronic health records (EHRs) for healthcare research. Despite the recognized importance of family health history, in healthcare research individual patients are often treated as independent samples, overlooking family relations. To address this gap, we present ALIGATEHR, which models predicted family relations in a graph attention network and integrates this information with a medical ontology representation. Taking disease risk prediction as a use case, we demonstrate that explicitly modeling family relations significantly improves predictions across the disease spectrum. We then show how ALIGATEHR’s attention mechanism, which links patients’ disease risk to their relatives’ clinical profiles, successfully captures genetic aspects of diseases using only EHR diagnosis data. Finally, we use ALIGATHER to successfully distinguish the two main inflammatory bowel disease subtypes (Crohn’s disease and ulcerative colitis), illustrating its great potential for improving patient representation learning for predictive and descriptive modeling of EHRs.Keywords
This publication has 42 references indexed in Scilit:
- Technological progress in electronic health record system optimization: Systematic review of systematic literature reviewsInternational Journal of Medical Informatics, 2021
- Standardized electronic health record data modeling and persistence: A comparative reviewJournal of Biomedical Informatics, 2021
- Active deep learning to detect demographic traits in free-form clinical notesJournal of Biomedical Informatics, 2020
- Disease Heritability Inferred from Familial Relationships Reported in Medical RecordsCell, 2018
- Heritability of Schizophrenia and Schizophrenia Spectrum Based on the Nationwide Danish Twin RegisterBiological Psychiatry, 2018
- The Heritability of Autism Spectrum DisorderJAMA, 2017
- Family history of inflammatory bowel disease among patients with ulcerative colitis: A systematic review and meta-analysisJournal of Crohn's and Colitis, 2014
- Design patterns for the development of electronic health record-driven phenotype extraction algorithmsJournal of Biomedical Informatics, 2014
- Use of an Electronic Medical Record to Create the Marshfield Clinic Twin/Multiple Birth CohortGenetic Epidemiology, 2014
- Family history of cancer and risk of sporadic differentiated thyroid carcinomaCancer, 2011