Machine learning in public health informatics: Evidence that complex sampling structures may not be needed for prediction models with imbalanced outcomes.

Journal: Annals of epidemiology

PMID: 39798678

Abstract

PURPOSE: The objective of this study is to investigate the predictive ability of machine learning models for imbalanced outcomes from national survey data without the use of sampling weights.

Authors

Zhengye Si

Department of Orthopaedic Surgery, Thompson Laboratory for Regenerative Orthopaedics, School of Medicine, University of Missouri, 1100 Virginia Avenue, Columbia , MO 65211, USA.
Jinpu Li

Department of Orthopaedic Surgery, Thompson Laboratory for Regenerative Orthopaedics, School of Medicine, University of Missouri, 1100 Virginia Avenue, Columbia , MO 65211, USA.
Emily Leary

Department of Orthopaedic Surgery, Thompson Laboratory for Regenerative Orthopaedics, School of Medicine, University of Missouri, 1100 Virginia Avenue, Columbia , MO 65211, USA. Electronic address: learye@health.missouri.edu.

Keywords

Female Humans Logistic Models Machine Learning Male Middle Aged Neural Networks, Computer Nutrition Surveys Public Health Public Health Informatics Support Vector Machine United States

External Resources

View on PubMed Access via DOI PubMed (39798678)

Machine learning in public health informatics: Evidence that complex sampling structures may not be needed for prediction models with imbalanced outcomes.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals