Characterizing personalized effects of family information on disease risk using graph representation learning

TL;DR

This paper introduces a graph-based deep learning method to analyze family medical histories from Finland's nationwide EHR system, improving disease risk prediction and enabling personalized insights into familial influences.

Contribution

It presents a novel explainable graph representation learning approach for modeling family history effects on disease risk using large-scale EHR data.

Findings

Improved 10-year disease onset prediction accuracy.

Enhanced personalization by identifying key relatives and features.

Effective use of graph explainability techniques.

Abstract

Family history is considered a risk factor for many diseases because it implicitly captures shared genetic, environmental and lifestyle factors. Finland's nationwide electronic health record (EHR) system spanning multiple generations presents new opportunities for studying a connected network of medical histories for entire families. In this work we present a graph-based deep learning approach for learning explainable, supervised representations of how each family member's longitudinal medical history influences a patient's disease risk. We demonstrate that this approach is beneficial for predicting 10-year disease onset for 5 complex disease phenotypes, compared to clinically-inspired and deep learning baselines for Finland's nationwide EHR system comprising 7 million individuals with up to third-degree relatives. Through the use of graph explainability techniques, we illustrate that a graph-based approach enables more personalized modeling of family information and disease risk by identifying important relatives and features for prediction.