Towards proactive palliative care in oncology: developing an explainable EHR-based machine learning model for mortality risk prediction.

Journal: BMC palliative care
PMID:

Abstract

BACKGROUND: Ex-ante identification of the last year in life facilitates a proactive palliative approach. Machine learning models trained on electronic health records (EHR) demonstrate promising performance in cancer prognostication. However, gaps in literature include incomplete reporting of model performance, inadequate alignment of model formulation with implementation use-case, and insufficient explainability hindering trust and adoption in clinical settings. Hence, we aim to develop an explainable machine learning EHR-based model that prompts palliative care processes by predicting for 365-day mortality risk among patients with advanced cancer within an outpatient setting.

Authors

  • Qingyuan Zhuang
    Division of Supportive and Palliative Care, National Cancer Centre Singapore, 30 Hospital Blvd, Singapore, 168583, Singapore. zhuang.qingyuan@singhealth.com.sg.
  • Alwin Yaoxian Zhang
    Division of Supportive and Palliative Care, National Cancer Centre Singapore, 30 Hospital Blvd, Singapore, 168583, Singapore.
  • Ryan Shea Tan Ying Cong
    Division of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore.
  • Grace Meijuan Yang
    Division of Supportive and Palliative Care, National Cancer Centre Singapore, 30 Hospital Blvd, Singapore, 168583, Singapore.
  • Patricia Soek Hui Neo
    Division of Supportive and Palliative Care, National Cancer Centre Singapore, 30 Hospital Blvd, Singapore, 168583, Singapore.
  • Daniel Sw Tan
    Division of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore.
  • Melvin Lk Chua
    Data Computational Science Core, National Cancer Centre Singapore, Singapore, Singapore.
  • Iain Beehuat Tan
    Division of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore.
  • Fuh Yong Wong
    Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore.
  • Marcus Eng Hock Ong
    Health Services Research Centre, SingHealth, Singapore.
  • Sean Shao Wei Lam
    Health Services Research Centre, SingHealth, Singapore.
  • Nan Liu
    Duke-NUS Medical School Centre for Quantitative Medicine Singapore Singapore.