Key result
LSTM models using raw IMU data accurately estimate VO2, demonstrating feasibility for noninvasive real-time monitoring.
Why the study?
Accurate assessment of training status in team sports is crucial for optimising performance and reducing injury risk, prompting investigation into machine learning models to estimate oxygen uptake from wearable sensors.
Can machine learning models using wearable sensor data accurately estimate oxygen uptake in team sports athletes?
Can machine learning models using wearable sensor data accurately estimate oxygen uptake in team sports athletes?
Machine learning models, particularly LSTM using raw IMU data, show potential for noninvasive, real-time estimation of oxygen uptake during team sports activities.
May support real-time VO2 monitoring in athletes; leaves open larger validation before adoption.
Accurate assessment of training status in team sports is crucial for optimising performance and reducing injury risk. This pilot study investigates the feasibility of using machine learning (ML) models to estimate oxygen uptake (VO2) with wearable sensors during team sports activities. Six healthy male team sports athletes participated in the study. Data were collected using inertial measurement units (IMU), heart rate monitors, and breathing rate sensors during incremental fitness tests. The performance of different ML models, including multiple linear regression (MLR), XGBoost, and deep learning models (LSTM, CNN, MLP), was compared using raw and engineered features from IMU data. Results indicate that while LSTM models with raw IMU data provided the most accurate predictions (RMSE: 4.976, MAE: 3.698 [Formula: see text]), MLR models remained competitive, especially with engineered features. Multi-sensor configurations, particularly those including sensors on the torso and limbs, enhanced prediction accuracy. The findings demonstrate the potential of ML models to monitor VO2 noninvasively in real-time, offering valuable insights into the internal physiological demand during team sports activities.
No takes yet. Share an insight, caveat, or question.
Sheridan et al. (2025) studied Healthy (n=6). Machine learning models with wearable sensor data vs. Different ML models and feature sets was evaluated on Oxygen uptake (VO2) estimation accuracy. LSTM models using raw IMU data provided the most accurate predictions for estimating oxygen uptake (RMSE 4.976, MAE 3.698), demonstrating the feasibility of noninvasive real-time VO2 monitoring.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: