Comparison of machine learning and conventional statistical modeling for predicting readmission following acute heart failure hospitalization.

Journal: American heart journal
PMID: 39094840

Abstract

INTRODUCTION: Developing accurate models for predicting the risk of 30-day readmission is a major healthcare interest. Evidence suggests that models developed using machine learning (ML) may have better discrimination than conventional statistical models (CSM), but the calibration of such models is unclear.

Authors

  • Karem Abdul-Samad
    Ted Rogers Centre for Heart Research, Toronto, Canada; University of Toronto, Toronto, Canada; ICES (formerly Institute for Clinical Evaluative Sciences), Toronto, Canada.
  • Shihao Ma
    Department of Computer Science, University of Toronto, Toronto, ON, Canada.
  • David E Austin
    ICES, Institute for Clinical Evaluative Sciences, 2075 Bayview Ave, Toronto, ON, M4N3M5, Canada.
  • Alice Chong
    Institute for Clinical Evaluative Service (ICES), Toronto, Ontario, Canada.
  • Chloe X Wang
    University Health Network, Toronto, Canada.
  • XueSong Wang
  • Peter C Austin
    Institute for Clinical Evaluative Service (ICES), Toronto, Ontario, Canada; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.
  • Heather J Ross
    Ted Rogers Centre for Heart Research, University of Toronto, Ontario, Canada (Y.M., F.F., Y.G., B.K., E.D.L., M.B., D.H.B., J.D., A.S., C.M.I., H.J.R.).
  • Bo Wang
    Department of Clinical Laboratory Medicine Center, Inner Mongolia Autonomous Region People's Hospital, Hohhot, Inner Mongolia, China.
  • Douglas S Lee
    Ted Rogers Centre for Heart Research, Toronto, Ontario, Canada; Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada; Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada; Institute for Health Policy, Management and Evaluation, Toronto, Ontario, Canada; Toronto General Hospital Research Institute, Toronto, Ontario, Canada; University of Toronto, Toronto, Ontario, Canada. Electronic address: dlee@ices.on.ca.

Keywords

External Resources

Popular Topics
Recent Journals