Enhancing patient representation learning with inferred family pedigrees improves disease risk prediction.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 39723811

Abstract

BACKGROUND: Machine learning and deep learning are powerful tools for analyzing electronic health records (EHRs) in healthcare research. Although family health history has been recognized as a major predictor for a wide spectrum of diseases, research has so far adopted a limited view of family relations, essentially treating patients as independent samples in the analysis.

Authors

  • Xiayuan Huang
    Department of Biostatistics, Yale University School of Public Health, New Haven, CT 06510, United States.
  • Jatin Arora
    Global Computational Biology and Digital Sciences, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riβ, Germany.
  • Abdullah Mesut Erzurumluoglu
    Global Computational Biology and Digital Sciences, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riβ, Germany.
  • Stephen A Stanhope
    Real World Data and Analytics, Global Medical Affairs, Boehringer Ingelheim, Ridgefield, CT 06877, United States.
  • Daniel Lam
    CB CMDR, Global Computational Biology and Digital Sciences, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riβ 88400, Germany.
  • Hongyu Zhao
    SJTU-Yale Joint Center for Biostatistics, Shanghai Jiao Tong University, 800 Dong Chuan Road, Shanghai 200240, China; Department of Biostatistics, Yale University, New Heaven, USA.
  • Zhihao Ding
    Global Computational Biology and Digital Sciences, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riβ, Germany.
  • Zuoheng Wang
    Department of Biostatistics, Yale School of Public Health, Yale University, New Haven, CT, United States.
  • Johann de Jong
    Global Computational Biology and Digital Sciences, Boehringer Ingelheim Pharma GmbH & Co. KG, Ingelheim 55216, Germany.

Keywords

External Resources

Popular Topics
Recent Journals