A Simulated Case Study for Application of Blood Pressure Parameters to predict Heart Rate

Cardiovascular stress monitoring plays a crucial role in managing hypertensive patients and preventing complications such as stroke or cardiac failure. This paper presents a novel approach using AI-based modeling to predict cardiovascular stress by analyzing blood pressure (BP) and heart rate (HR) data. Simulated datasets representing two patient profiles (normal and abnormal) were generated over a 6-month period. We applied linear regression to model the relationship between systolic BP and HR, achieving a prediction accuracy with R² = 0.72 and MAPE = 3.51%. The system identifies high-risk episodes using co-occurrence logic (BP > 180 mmHg and predicted HR > 100 bpm), enabling early warnings. Performance was evaluated using RMSE, MAPE, and NRMSE. The results show the potential of simple, interpretable predictive models in proactive cardiovascular health monitoring.