Article

Learning lifetime disease liability reveals and removes genetic confounding in electronic health records

2026-02-22

Abstract excerpt

Electronic health records (EHRs) have become the cornerstone of population-scale genetic studies 1 , but factors including patterns of healthcare use shape which and how diagnoses are recorded, leading to confounding effects in genetic associations with EHR codes 2 . In this study we propose EDGAR, a deep learning framework that recovers lifetime disease liability from EHR by aligning diagnostic codes with clini...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 09c52149-46f1-5ea4-9acd-2a394a899a88
DOI: 10.64898/2026.02.15.26346336

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Learning lifetime disease liability reveals and removes genetic confounding in electronic health recordsDOI 10.64898/2026.02.15.26346336Read

Transferability and accuracy of electronic health record-based predictors compared to polygenic scoresSemantic proximity Read

Estimating heritability and genetic correlations from large health datasets in the absence of genetic data.Semantic proximity Read

Reducing misclassification bias in electronic health record-based GWAS of psychiatric traits using the SuperControl frameworkSemantic proximity Read

A deep learning transformer model predicts high rates of undiagnosed rare disease in large electronic health systemsSemantic proximity Read

Machine learning approaches for electronic health records phenotyping: a methodical review.Semantic proximity Read

Machine Learning Approaches for Electronic Health Records Phenotyping: A Methodical ReviewSemantic proximity Read

Learning the shared structure of human health across diseases, modalities, and timeSemantic proximity Read

Learning probabilistic phenotypes from heterogeneous EHR data.Semantic proximity Read

PRSformer: Disease Prediction from Million-Scale Individual GenotypesSemantic proximity Read

RubricOE: a learning framework for genetic epidemiologySemantic proximity Read

POPDx: an automated framework for patient phenotyping across 392 246 individuals in the UK Biobank study.Semantic proximity Read

Machine Learning to Advance Human Genome‐Wide Association StudiesSemantic proximity Read