Back

Reinventing the Body Mass Index: A Machine Learning Approach

Peregrin-Alvarez, J. M.

2024-04-29 health informatics
10.1101/2024.04.26.24306457 medRxiv
Show abstract

This study explores the predictive capabilities of the Body Mass Index (BMI) formula across a diverse dataset, examining the potential enhancements achievable through integrating additional parameters using machine learning (ML) models. Various modern ML models were utilized (K-Nearest Neighbors, Neural Networks, Decision Trees, Support Vector Classification, Logistic Regression, and Ridge Classifiers. Ensemble models: voting Classifier, Random Forest, and Gradient Boosting), demonstrating improved accuracy and precision over the traditional BMI calculations. Incorporating age and gender into BMI calculations together with the best performing ML model such as Gradient Boosting offers promise for more accurate and personalized health assessments, with significant implications for clinical practice and public health interventions.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.