Optimizing VO₂max Prediction in Gamified Cardiac Assessment: Leveraging Effective Feature Selection and Refined Protocols for Robust Models

VO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>max is a critical indicator of cardiopulmonary fitness, reflecting the maximum amount of oxygen the body can utilize during intense exercise. Accurately measuring VO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>max is essential for assessing cardiovascular health and predicting outcomes in clinical settings. However, current methods for VO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>max estimation, such as Cardiopulmonary Exercise Testing (CPET), require expensive equipment and the supervision of trained personnel, limiting accessibility for large-scale screening and prognostic purposes. Preliminary efforts have been made to create a more accessible method, such as the Cardiopulmonary Spot Jog Test (CPSJT). Unfortunately, these early attempts yielded high error margins, rendering them unsuitable for widespread use. In our study, we address these shortcomings by refining the CPSJT protocol to improve prediction accuracy. A key modification involved adjusting the CPSJT's cutoff point based on each participant's CPET-derived maximum heart rate (HR) rather than relying on a fixed percentage of theoretical max HR. This change provides a more individualized and accurate reflection of endurance. Our second crucial contribution is improved feature extraction and feature selection which include gender, body mass index, aerobic duration, and anaerobic duration. This targeted approach to feature extraction helps in streamlining the model to enhance prediction precision while minimizing the risk of overfitting. In a cohort of 44 participants from the Indian population, we assessed the performance of various machine learning models using these features. With Stratified 5-Fold Cross-Validation, the Root Mean Squared Error (RMSE) values were 5.78 for Linear Regression, 5.15 for Random Forest (RF), and 5.17 for Support Vector Regression (SVR). All models demonstrated strong test correlations and low RMSE values, underscoring their robust and reliable performance. This study highlights the potential of our enhanced CPSJT protocol in providing a more accessible and reliable method for non-invasive cardiovascular fitness evaluation, offering a promising alternative to traditional exercise testing methods.