Back

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

2026-02-22 genetic and genomic medicine Title + abstract only
View on medRxiv
Show abstract

Electronic health records (EHRs) have become the cornerstone of population-scale genetic studies1, but factors including patterns of healthcare use shape which and how diagnoses are recorded, leading to confounding effects in genetic associations with EHR codes2. In this study we propose EDGAR, a deep learning framework that recovers lifetime disease liability from EHR by aligning diagnostic codes with clinically validated measures and disease labels in a set of individuals prioritized through a...

Predicted journal destinations

1
Nature Communications
483 training papers
Top 5% 14.2%
2
The American Journal of Human Genetics
77 training papers
Top 0.7% 14.2%
3
Scientific Reports
701 training papers
Top 14% 11.5%
4
Nature Genetics
72 training papers
Top 1% 7.6%
5
Genetics in Medicine
57 training papers
Top 3% 4.9%
6
Genome Medicine
56 training papers
Top 2% 4.9%
7
Bioinformatics
24 training papers
Top 0.2% 4.0%
8
PLOS Genetics
39 training papers
Top 0.6% 4.0%
9
Cell Genomics
34 training papers
Top 1% 3.0%
10
Communications Biology
36 training papers
Top 0.5% 1.9%
11
Human Genetics and Genomics Advances
39 training papers
Top 4% 1.9%
12
Proceedings of the National Academy of Sciences
100 training papers
Top 6% 1.9%
13
PLOS ONE
1737 training papers
Top 93% 1.9%
14
European Journal of Human Genetics
25 training papers
Top 3% 1.5%
15
npj Digital Medicine
85 training papers
Top 13% 1.5%
16
Human Molecular Genetics
28 training papers
Top 5% 1.3%
17
npj Genomic Medicine
18 training papers
Top 2% 1.3%
18
eLife
262 training papers
Top 35% 1.3%
19
Frontiers in Genetics
32 training papers
Top 6% 1.1%
20
Nature
58 training papers
Top 6% 1.1%
21
Translational Psychiatry
94 training papers
Top 9% 0.9%
22
Nature Medicine
88 training papers
Top 13% 0.9%
23
Circulation: Genomic and Precision Medicine
30 training papers
Top 7% 0.7%
24
Genes
21 training papers
Top 5% 0.7%
25
Journal of the American Medical Informatics Association
53 training papers
Top 6% 0.7%
26
Science Advances
52 training papers
Top 6% 0.7%
27
PLOS Computational Biology
141 training papers
Top 15% 0.7%