What is it about?

In this paper, artificial intelligence is used to figure out why obesity prevalence differs between U.S. counties. Machine learning models are often a mystery, but this paper shows how to interpret them. Using county-level information, the machine learning models showed that places that have more obesity also exercise less and smoke more. Understanding this can help us tackle obesity in different areas.

Featured Image

Why is it important?

This paper pioneers the application of explainable artificial intelligence in untangling the complexity of obesity. By enhancing transparency and interpretability of machine learning models it establishes a new standard for interpreting machine learning models for health. The unique contribution lies in its ability to unveil what machine learning models discover, exposing critical factors like physical inactivity that contribute to obesity. This transparency not only deepens our understanding of the disease but also enables the customization of treatment plans through local interpretable model-agnostic explanations. This approach can empower researchers and clinicians to address the unique characteristics and needs of individual counties or patients.


Interpretable machine learning models of health behaviors and outcomes provide substantial insight into obesity prevalence variation across counties in the United States.

Ben Allen

Read the Original

This page is a summary of: An interpretable machine learning model of cross-sectional U.S. county-level obesity prevalence using explainable artificial intelligence, PLoS ONE, October 2023, PLOS,
DOI: 10.1371/journal.pone.0292341.
You can read the full text:

Open access logo



The following have contributed to this page