Physiological Age Detection Using ECG: A Machine Learning-Based Framework

This study uses ECG data to introduce a machinelearning framework to detect physiological age. Ten classifiers were evaluated on unaltered and balanced data, with further analysis of the balanced data with and without additional preprocessing steps. The Random Forest classifier achieved the best accuracy of 80%, even without extensive preprocessing, highlighting the critical role of proper data balancing techniques. These findings demonstrate the potential of machine learning to support early lifestyle interventions, helping to improve overall health and well-being. The study underscores the significance of data preparation techniques in maximizing the performance and accuracy of machine learning models in healthcare applications.