Heart Disease Prediction using Reinforcement Learning Technique
Kamepalli S. L. Prasanna, Nagendra Panini Challa, Jajam. Nagaraju
Abstract
Heart Disease (HD) is one of the most common lifestyle diseases caused by high blood pressure. A lack of stress in the workplace causes an unmanageable rise in blood pressure, which can lead to life-threatening serious circumstances. The early-stage diagnosis of heart disease is essential to saving several people's life. This paper provides an ML knowledge-based forecast model for detecting heart disease. The Q-learning technique from the RL (Reinforcement Learning) framework was used for the Cleveland heart disease dataset in the prediction method. The framework depicts patients with heart disease utilizing 3 main factors: trestbps, Chol, and age by developing the off-premised RL and instructing the learning agent to determine the best rule for the attributes. The proposed RL method accuracy, recall, precision, AUC, and F-measure values were evaluated with cutting-edge methods like KNN and DT. The proposed RL-based heart disease forecasting outperforms the KNN and DT techniques.