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

Sophie Wharrie, Zhiyu Yang, Andrea Ganna, Samuel Kaski
Proceedings of the 8th Machine Learning for Healthcare Conference, PMLR 219:824-845, 2023.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v219-wharrie23a, title = {Characterizing personalized effects of family information on disease risk using graph representation learning}, author = {Wharrie, Sophie and Yang, Zhiyu and Ganna, Andrea and Kaski, Samuel}, booktitle = {Proceedings of the 8th Machine Learning for Healthcare Conference}, pages = {824--845}, year = {2023}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo and Yeung, Serene}, volume = {219}, series = {Proceedings of Machine Learning Research}, month = {11--12 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v219/wharrie23a/wharrie23a.pdf}, url = {https://proceedings.mlr.press/v219/wharrie23a.html}, 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.} }
Endnote
%0 Conference Paper %T Characterizing personalized effects of family information on disease risk using graph representation learning %A Sophie Wharrie %A Zhiyu Yang %A Andrea Ganna %A Samuel Kaski %B Proceedings of the 8th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2023 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %E Serene Yeung %F pmlr-v219-wharrie23a %I PMLR %P 824--845 %U https://proceedings.mlr.press/v219/wharrie23a.html %V 219 %X 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.
APA
Wharrie, S., Yang, Z., Ganna, A. & Kaski, S.. (2023). Characterizing personalized effects of family information on disease risk using graph representation learning. Proceedings of the 8th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 219:824-845 Available from https://proceedings.mlr.press/v219/wharrie23a.html.

Related Material