Enhancing Cardiovascular Risk Assessment: A Fusion of HRV and Wavelet Transform for Hypertension Patients

Diagnosing the disease is the most critical functionality of health care. Forecasting cardiovascular as well as cerebrovascular events in people with hypertension is considered to be particularly significant for controlling the progression of heart disorders. Although numerous gold-standard approaches are capable of forecasting the likelihood of vascular events, they often lack the required clinical efficacy. In this context, the study proposed here investigates individuals with hypertension who are more likely to experience cardiac events when Heart Rate Variability (HRV) and Wavelet Transform (WT) are combined in a machine-learning approach. Initially, all patient information was retrieved for HRV features utilizing the time-domain and frequency domain in the afternoon time period (12:00–18:00). Then, the daubuche(db1) wavelet transform was used to extract energy features from all patient data. Subsequently, employing combinations like HRV and wavelet, a model based on random under-sampling boosting (RUSboost) was trained. This study provides a path to the use of Wavelet Transform characteristics, Heart Rate Variability, and Machine Learning models to predict vascular events in hypertension patients. When compared to other existing methodologies, it also supports practitioners in decision-making by offering a simple yet effective prediction strategy