An AI-Based Exercise Prescription Recommendation System

The European Association of Preventive Cardiology Exercise Prescription in Everyday Practice and Rehabilitative Training (EXPERT) tool has been developed for digital training decision support cardiovascular disease patients clinical practice. prescription recommendation systems sub-healthy people are essential to enhance this dominant group’s physical ability as well. This study aims construct a guided exercise system groups using community data train an AI model. consists six modules, including three-month suggested mode (3m-SEM), predicted value rest heart rate (rest HR) difference after following (3m-PV), two-month (2m-SEM), HR (2m-PV), one-month (1m-SEM) (1m-PV). A new user inputs gender, height, weight, age, current value, the above modules will provide with prescription. four-layer neural network model is applied modules. AI-enabled produced 95.80%, 100.00%, 95.00% testing accuracy 1m-SEM, 2m-SEM, 3m-SEM, respectively. It reached 3.15, 2.89, 2.75 BPM mean absolute error 1m-PV, 2m-PV, 3m-PV. provides quantitative prescriptions guide group engage effective programs.