Preparing for the bedside-optimizing a postpartum depression risk prediction model for clinical implementation in a health system.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 38531676

Abstract

OBJECTIVE: We developed and externally validated a machine-learning model to predict postpartum depression (PPD) using data from electronic health records (EHRs). Effort is under way to implement the PPD prediction model within the EHR system for clinical decision support. We describe the pre-implementation evaluation process that considered model performance, fairness, and clinical appropriateness.

Authors

  • Yifan Liu
    College of Orthopedics and Traumatology, Henan University of Chinese Medicine, Zhengzhou, China.
  • Rochelle Joly
    Department of Obstetrics and Gynecology, Weill Cornell Medicine, New York, NY 10065, United States.
  • Meghan Reading Turchioe
    Department of Population Health Sciences, Division of Health Informatics, Weill Cornell Medicine, New York, New York, USA mjr2011@med.cornell.edu.
  • Natalie Benda
    Columbia University School of Nursing, New York, NY, United States.
  • Alison Hermann
    Department of Psychiatry, Weill Cornell Medicine, New York, NY, United States.
  • Ashley Beecy
    Division of Cardiology, Department of Medicine, Weill Cornell Medicine and NewYork-Presbyterian, New York, NY, USA.
  • Jyotishman Pathak
    Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA.
  • Yiye Zhang
    Department of Healthcare Policy and Research, Weill Cornell Medical College/New York Presbyterian, NY, USA.

Keywords

External Resources

Popular Topics
Recent Journals