Machine learning predicts peak oxygen uptake and peak power output for customizing cardiopulmonary exercise testing using non-exercise features.

Journal: European journal of applied physiology
PMID:

Abstract

PURPOSE: Cardiopulmonary exercise testing (CPET) is considered the gold standard for assessing cardiorespiratory fitness. To ensure consistent performance of each test, it is necessary to adapt the power increase of the test protocol to the physical characteristics of each individual. This study aimed to use machine learning models to determine individualized ramp protocols based on non-exercise features. We hypothesized that machine learning models will predict peak oxygen uptake ( O) and peak power output (PPO) more accurately than conventional multiple linear regression (MLR).

Authors

  • Charlotte Wenzel
    Institute for Sport and Sport Science, Performance and Health (Sports Medicine), TU Dortmund University, Dortmund, Germany.
  • Thomas Liebig
    Institute of Neuroradiology, University Hospital, LMU Munich, Munich, Germany.
  • Adrian Swoboda
    Institute for Training Optimization for Sport and Health, iQ Athletik, Frankfurt am Main, Germany.
  • Rika Smolareck
    Institute for Sport and Sport Science, Performance and Health (Sports Medicine), TU Dortmund University, Dortmund, Germany.
  • Marit L Schlagheck
    Institute for Sport and Sport Science, Performance and Health (Sports Medicine), TU Dortmund University, Dortmund, Germany.
  • David Walzik
    Institute for Sport and Sport Science, Performance and Health (Sports Medicine), TU Dortmund University, Dortmund, Germany.
  • Andreas Groll
    Department of Statistics, TU Dortmund University, Dortmund, Germany.
  • Richie P Goulding
    Faculty of Behavioral and Movement Sciences, Department of Human Movement Sciences, Vrije Universiteit Amsterdam, Amsterdam Movement Sciences, Amsterdam, The Netherlands.
  • Philipp Zimmer
    Institute for Sport and Sport Science, Performance and Health (Sports Medicine), TU Dortmund University, Dortmund, Germany. philipp.zimmer@tu-dortmund.de.