Mitigating underreported error in food frequency questionnaire data using a supervised machine learning method and error adjustment algorithm.

Journal: BMC medical informatics and decision making

PMID: 37689645

Abstract

BACKGROUND: Food frequency questionnaires (FFQs) are one of the most useful tools for studying and understanding diet-disease relationships. However, because FFQs are self-reported data, they are susceptible to response bias, social desirability bias, and misclassification. Currently, several methods have been created to combat these issues by modelling the measurement error in diet-disease relationships.

Authors

Anjolaoluwa Ayomide Popoola

Georgia Institute of Technology, Atlanta, GA, USA.
Jennifer Koren Frediani

Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, GA, USA.
Terryl Johnson Hartman

Rollins School of Public Health, Emory University, Atlanta, GA, USA.
Kamran Paynabar

Georgia Institute of Technology, Atlanta, GA, USA. kpaynabar3@gatech.edu.

Keywords

Algorithms Humans Machine Learning Random Forest Self Report Supervised Machine Learning

External Resources

View on PubMed Access via DOI PubMed (37689645)

Mitigating underreported error in food frequency questionnaire data using a supervised machine learning method and error adjustment algorithm.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals