Predicting Body Fat Percentage from Simple Anthropometric Measurements: A Machine Learning Approach.

Journal: Studies in health technology and informatics
PMID:

Abstract

Accurately assessing body fat percentage (BF%) is crucial for healthcare and fitness but is hindered by gold-standard methods that are costly and invasive. This study employs a dataset containing variables such as age, sex, Body Mass Index (BMI), and body circumferences, from individuals whose body fat percentage (BF%) was estimated via underwater weighing, to develop predictive machine learning models. Multiple regression techniques alongside a neural network were employed to compare model accuracies in estimating BF%. Ridge Regression emerged as the most effective model, demonstrating the highest R2 score. Notably, feature importance analysis using ElasticNet and SHAP revealed that abdominal circumference was the most significant predictor of BF%, challenging the adequacy of BMI as a measure of adiposity. These insights advocate for the broader adoption of circumference measurements in everyday practice to enhance the predictive accuracy of cost-effective and easily performed BF% estimation.

Authors

  • Nikolaos Theodorakis
    Department of Cardiology, Amalia Fleming General Hospital, Athens, Greece.
  • Georgios Feretzakis
    School of Science and Technology, Hellenic Open University, Patras, Greece.
  • Magdalini Kreouzi
    Department of Internal Medicine, Amalia Fleming General Hospital, Athens, Greece.
  • Olga Fafoula
    Pediatric Endocrinology Outpatient Clinic, Penteli General Children's Hospital, Penteli, Greece.
  • Christos Hitas
    Department of Cardiology, Amalia Fleming General Hospital, Athens, Greece.
  • Sofia Kalantzi
    65+ Clinic, Amalia Fleming General Hospital, Athens, Greece.
  • Aikaterini Spyridaki
    65+ Clinic, Amalia Fleming General Hospital, Athens, Greece.
  • Effrosyni Bazakidou
    Medical School, Humanitas University, Milan, Italy.
  • Iris Zoe Boufeas
    Barts and The London School of Medicine and Dentistry, Queen Mary University of London, UK.
  • Dimitris Kalles
    School of Science and Technology, Hellenic Open University, Patras, Greece.
  • Vassilios S Verykios
    School of Science and Technology, Hellenic Open University, Patras, Greece.
  • Maria Nikolaou
    Department of Cardiology, Amalia Fleming General Hospital, Athens, Greece.