Novel Pediatric Height Outlier Detection Methodology for Electronic Health Records via Machine Learning With Monotonic Bayesian Additive Regression Trees.

Journal: Journal of pediatric gastroenterology and nutrition
Published Date:

Abstract

OBJECTIVE: To create a new methodology that has a single simple rule to identify height outliers in the electronic health records (EHR) of children.

Authors

  • Rodney A Sparapani
    From the Division of Biostatistics, Medical College of Wisconsin, Milwaukee, WI.
  • Bi Q Teng
    From the Division of Biostatistics, Medical College of Wisconsin, Milwaukee, WI.
  • Julia Hilbrands
    the Clinical Nutrition, Children's Wisconsin, Milwaukee, WI.
  • Rebecca Pipkorn
    the Clinical Nutrition, Children's Wisconsin, Milwaukee, WI.
  • Mary Beth Feuling
    the Clinical Nutrition, Children's Wisconsin, Milwaukee, WI.
  • Praveen S Goday
    the Pediatric Gastroenterology and Nutrition, Medical College of Wisconsin, Milwaukee, WI.