Development of a Machine Learning Model Using Multiple, Heterogeneous Data Sources to Estimate Weekly US Suicide Fatalities.

Journal: JAMA network open
Published Date:

Abstract

IMPORTANCE: Suicide is a leading cause of death in the US. However, official national statistics on suicide rates are delayed by 1 to 2 years, hampering evidence-based public health planning and decision-making.

Authors

  • Daejin Choi
    Department of Computer Science and Engineering, Incheon National University, Incheon, South Korea.
  • Steven A Sumner
    Office of Strategy and Innovation, National Center for Injury Prevention and Control, Centers for Disease Control and Prevention, Atlanta, Georgia.
  • Kristin M Holland
    Division of Violence Prevention, National Center for Injury Prevention and Control, Centers for Disease Control and Prevention, Atlanta, Georgia.
  • John Draper
    National Suicide Prevention Lifeline, New York, New York.
  • Sean Murphy
    National Suicide Prevention Lifeline, New York, New York.
  • Daniel A Bowen
    Division of Violence Prevention, National Center for Injury Prevention and Control, Centers for Disease Control and Prevention, Atlanta, Georgia.
  • Marissa Zwald
    Division of Violence Prevention, National Center for Injury Prevention and Control, Centers for Disease Control and Prevention, Atlanta, Georgia.
  • Jing Wang
    Endoscopy Center, Peking University Cancer Hospital and Institute, Beijing, China.
  • Royal Law
    National Center for Environmental Health, Centers for Disease Control and Prevention, Atlanta, Georgia.
  • Jordan Taylor
    School of Interactive Computing, Georgia Institute of Technology, Atlanta.
  • Chaitanya Konjeti
    School of Interactive Computing, Georgia Institute of Technology, Atlanta.
  • Munmun DE Choudhury
    Georgia Institute of Technology, USA.