Machine Learning Models for the Automatic Detection of Exercise Thresholds in Cardiopulmonary Exercising Tests: From Regression to Generation to Explanation

The role of machine learning methods in physiological explorations of endurance trained athletes: a mini-review

Endurance-trained athletes require physiological explorations that have evolved throughout the history of exercise physiology with technological advances. From the use of the Douglas bag to measure gas exchange to the development of wearable connected devices, advances in physiological explorations have enabled us to move from the classic but still widely used cardiopulmonary exercise test (CPET) to the collection of data under real conditions on outdoor endurance or ultra-endurance events. However, such explorations are often costly, time-consuming, and complex, creating a need for efficient analysis methods. Machine Learning (ML) has emerged as a powerful tool in exercise physiology, offering solutions to these challenges. Given that exercise physiologists may be unfamiliar with ML, this mini-review provides a concise overview of its relevance to the field. It introduces key ML methods, highlights their ability to predict important physiological parameters (e.g., heart rate variability and exercise-induced hypoxemia), and discusses their strengths and limitations. Finally, it outlines future directions based on the challenges identified, serving as an initial reference for physiologists exploring the application of ML in endurance exercise.

Unlocking the potential of artificial intelligence in sports cardiology: does it have a role in evaluating athlete's heart?

The integration of artificial intelligence (AI) technologies is evolving in different fields of cardiology and in particular in sports cardiology. Artificial intelligence offers significant opportunities to enhance risk assessment, diagnosis, treatment planning, and monitoring of athletes. This article explores the application of AI in various aspects of sports cardiology, including imaging techniques, genetic testing, and wearable devices. The use of machine learning and deep neural networks enables improved analysis and interpretation of complex datasets. However, ethical and legal dilemmas must be addressed, including informed consent, algorithmic fairness, data privacy, and intellectual property issues. The integration of AI technologies should complement the expertise of physicians, allowing for a balanced approach that optimizes patient care and outcomes. Ongoing research and collaborations are vital to harness the full potential of AI in sports cardiology and advance our management of cardiovascular health in athletes.

Estimation of physiological exercise thresholds based on dynamical correlation properties of heart rate variability

Aerobic and anaerobic thresholds of the three-zone exercise model are often used to evaluate the exercise intensity and optimize the training load. Conventionally, these thresholds are derived from the respiratory gas exchange or blood lactate concentration measurements. Here, we introduce and validate a computational method based on the RR interval (RRI) dynamics of the heart rate (HR) measurement, which enables a simple, yet reasonably accurate estimation of both metabolic thresholds. The method utilizes a newly developed dynamical detrended fluctuation analysis (DDFA) to assess the real-time changes in the dynamical correlations of the RR intervals during exercise. The training intensity is shown to be in direct correspondence with the time- and scale-dependent changes in the DDFA scaling exponent. These changes are further used in the definition of an individual measure to estimate the aerobic and anaerobic threshold. The results for 15 volunteers who participated in a cyclo-ergometer test are compared to the benchmark lactate thresholds, as well as to the ventilatory threshods and alternative HR-based estimates based on the maximal HR and the conventional detrended fluctuation analysis (DFA). Our method provides the best overall agreement with the lactate thresholds and provides a promising, cost-effective alternative to conventional protocols, which could be easily integrated in wearable devices. However, detailed statistical analysis reveals the particular strengths and weaknessess of each method with respect to the agreement and consistency with the thresholds-thus underlining the need for further studies with more data.