Applying machine learning approaches for predicting obesity risk using US health administrative claims database.

Journal: BMJ open diabetes research & care

PMID: 39327067

Abstract

INTRODUCTION: Body mass index (BMI) is inadequately recorded in US administrative claims databases. We aimed to validate the sensitivity and positive predictive value (PPV) of BMI-related diagnosis codes using an electronic medical records (EMR) claims-linked database. Additionally, we applied machine learning (ML) to identify features in US claims databases to predict obesity status.

Authors

Casey Choong

Eli Lilly and Company, Indianapolis, Indiana, USA choong_kar-chan@lilly.com.
Alan Brnabic

Eli Lilly and Company, Sydney, NSW, Australia.
Chanadda Chinthammit

Eli Lilly and Company, Indianapolis, Indiana, USA.
Meena Ravuri

Eli Lilly and Company, Indianapolis, Indiana, USA.
Kendra Terrell

Eli Lilly and Company, Indianapolis, Indiana, USA.
Hong Kan

Eli Lilly and Company Indianapolis Indiana USA.

Keywords

Administrative Claims, Healthcare Adolescent Adult Aged Body Mass Index Databases, Factual Electronic Health Records Female Humans Machine Learning Male Middle Aged Obesity Prognosis Retrospective Studies Risk Assessment Risk Factors ROC Curve United States Young Adult

External Resources

View on PubMed Access via DOI PubMed (39327067)

Applying machine learning approaches for predicting obesity risk using US health administrative claims database.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals