Forecasting Pediatric Trauma Volumes: Insights From a Retrospective Study Using Machine Learning.

Journal: The Journal of surgical research
PMID:

Abstract

INTRODUCTION: Rising pediatric firearm-related fatalities in the United States strain Trauma Centers. Predicting trauma volume could improve resource management and preparedness, particularly if daily forecasts are achievable. The aim of the study is to evaluate various machine learning models' accuracy on monthly, weekly, and daily data.

Authors

  • Ayaka Tsutsumi
    Department of Pediatric Surgery, SSM Health Cardinal Glennon Children's Hospital, St. Louis, Missouri; Department of Pediatric Surgery, St. Louis University, St. Louis, Missouri. Electronic address: ayaka.tsutsumi@health.slu.edu.
  • Chiara Camerota
    Department of Computer Science, St. Louis University, St. Louis, Missouri.
  • Flavio Esposito
    Department of Computer Science, St. Louis University, St. Louis, Missouri.
  • Si-Min Park
    Department of Pediatric Surgery, SSM Health Cardinal Glennon Children's Hospital, St. Louis, Missouri; Department of Pediatric Surgery, St. Louis University, St. Louis, Missouri.
  • Tiffany Taylor
    Department of Pediatric Surgery, SSM Health Cardinal Glennon Children's Hospital, St. Louis, Missouri; Department of Pediatric Surgery, St. Louis University, St. Louis, Missouri.
  • Shin Miyata
    Department of Pediatric Surgery, SSM Health Cardinal Glennon Children's Hospital, St. Louis, Missouri; Department of Pediatric Surgery, St. Louis University, St. Louis, Missouri.