Athletes pushing their bodies to the limit can sometimes lead to cardiovascular diseases (CVDs). These issues affect the heart and blood vessels, making early detection crucial. A new method has been developed to spot these problems using artificial intelligence. This method uses a special kind of artificial neural network (ANN) to analyze data. The ANN is trained using a unique algorithm called mutual learning-based artificial bee colony (ML-ABC). This algorithm helps the ANN find the best starting points by learning from two random individuals. The ML-ABC algorithm improves the learning process by updating the positions of the food sources with respect to the best fitness outcomes of two randomly selected individuals.

        The ANN also uses a technique called proximal policy optimisation (PPO) to make sure the updates are stable and efficient. This helps the model become more reliable. The PPO technique handles class imbalance by rewarding correct classifications, especially for the minority class. This means the model is better at identifying rare but important cases. The model was tested on a large dataset of 26, 002 athletes from the Polyclinic for Occupational Health and Sports in Zagreb. To ensure the model works well in different situations, it was also validated with datasets from the NCAA and NHANES.

        The results were impressive, with accuracies of 0. 88, 0. 86, and 0. 82 for the respective datasets. This shows that the model is not only accurate but also versatile. The findings suggest that this approach could be a game-changer in clinical settings, making it easier to detect cardiovascular disorders. By using this method, doctors can catch heart issues early, which could save lives. However, it's important to note that while this method shows promise, it's just one tool in the toolkit. More research and real-world testing are needed to fully understand its potential and limitations.

Detecting Heart Issues in Athletes: A Smart Approach

Actions