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

Sophie Wharrie, Samuel Kaski

Research output: Contribution to conferencePaperpeer-review


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.
Original languageEnglish
Number of pages22
Publication statusPublished - 2023
EventMachine Learning for Healthcare (MLHC) - New York, United States - New York, United States
Duration: 11 Aug 202312 Aug 2023
Conference number: 8th


ConferenceMachine Learning for Healthcare (MLHC) - New York, United States
Country/TerritoryUnited States
CityNew York
Internet address


  • Machine learning
  • Deep learning
  • medical history
  • disease risk

Research Beacons, Institutes and Platforms

  • Christabel Pankhurst Institute
  • Digital Futures
  • Institute for Data Science and AI
  • Sustainable Futures


Dive into the research topics of 'Characterizing personalized effects of family information on disease risk using graph representation learning'. Together they form a unique fingerprint.

Cite this