Estimation of total body fat using symbolic regression and evolutionary algorithms

2025-03-01

AI Summary

This study addresses the clinical need for accurate and interpretable body fat percentage prediction. Methodologically, it proposes an evolutionary algorithm–driven symbolic regression framework and systematically compares three grammar-guided approaches—Grammatical Evolution (GE), CFG-GP, and Deterministic Symbolic Graph Evolution (DSGE)—on public anthropometric datasets to automatically discover concise, explicit algebraic formulas (e.g., involving height, weight, and waist circumference). Its key contribution is the first empirical validation demonstrating DSGE’s superiority in balancing interpretability and accuracy, outperforming state-of-the-art methods such as QLattice. Experimental results show that the generated models achieve a mean absolute error (MAE) < 2.5%, matching the predictive performance of black-box models, while yielding physiologically meaningful, clinically actionable formulas suitable for direct deployment in healthcare settings.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Evolutionary Learning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Body fat percentage is an increasingly popular alternative to Body Mass Index to measure overweight and obesity, offering a more accurate representation of body composition. In this work, we evaluate three evolutionary computation techniques, Grammatical Evolution, Context-Free Grammar Genetic Programming, and Dynamic Structured Grammatical Evolution, to derive an interpretable mathematical expression to estimate the percentage of body fat that are also accurate. Our primary objective is to obtain a model that balances accuracy with explainability, making it useful for clinical and health applications. We compare the performance of the three variants on a public anthropometric dataset and compare the results obtained with the QLattice framework. Experimental results show that grammatical evolution techniques can obtain competitive results in performance and interpretability.

Problem

• Develop interpretable models for body fat estimation
• Compare evolutionary algorithms for accuracy and explainability
• Evaluate models on anthropometric data for clinical use

Innovation

• Symbolic regression for body fat estimation
• Evolutionary algorithms enhance model interpretability
• Grammatical evolution techniques optimize accuracy