Saved in:
Bibliographic Details
Main Authors: Wharrie, Sophie, Yang, Zhiyu, Ganna, Andrea, Kaski, Samuel
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2304.05010
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917606934446080
author Wharrie, Sophie
Yang, Zhiyu
Ganna, Andrea
Kaski, Samuel
author_facet Wharrie, Sophie
Yang, Zhiyu
Ganna, Andrea
Kaski, Samuel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_05010
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Characterizing personalized effects of family information on disease risk using graph representation learning
Wharrie, Sophie
Yang, Zhiyu
Ganna, Andrea
Kaski, Samuel
Applications
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.
title Characterizing personalized effects of family information on disease risk using graph representation learning
topic Applications
url https://arxiv.org/abs/2304.05010