Incorporating machine learning and social determinants of health indicators into prospective risk adjustment for health plan payments.

Journal: BMC public health
PMID: 32357871

Abstract

BACKGROUND: Risk adjustment models are employed to prevent adverse selection, anticipate budgetary reserve needs, and offer care management services to high-risk individuals. We aimed to address two unknowns about risk adjustment: whether machine learning (ML) and inclusion of social determinants of health (SDH) indicators improve prospective risk adjustment for health plan payments.

Authors

  • Jeremy A Irvin
    Department of Computer Science, Stanford University, 353 Serra Mall, Stanford, CA, 94305, USA. jirvin16@cs.stanford.edu.
  • Andrew A Kondrich
    Department of Computer Science, Stanford University, 353 Serra Mall, Stanford, CA, 94305, USA.
  • Michael Ko
    Department of Statistics, Stanford University, Stanford, USA.
  • Pranav Rajpurkar
    Harvard Medical School, Department of Biomedical Informatics, Cambridge, MA, 02115, US.
  • Behzad Haghgoo
    Department of Computer Science, Stanford University, 353 Serra Mall, Stanford, CA, 94305, USA.
  • Bruce E Landon
    Department of Healthcare Policy, Harvard Medical School, Boston, USA.
  • Robert L Phillips
    Center for Professionalism & Value in Health Care, American Board of Family Medicine Foundation, Lexington, USA.
  • Stephen Petterson
    Robert Graham Center, American Academy of Family Physicians, Leawood, USA.
  • Andrew Y Ng
  • Sanjay Basu
    Center for Primary Care and Outcomes Research, Center for Population Health Sciences, Departments of Medicine and Health Research and Policy, Stanford University, Palo Alto, CA basus@stanford.edu.

Keywords

External Resources

Popular Topics
Recent Journals