Toward Hypertension Prediction Based on PPG-Derived HRV Signals: a Feasibility Study

Area of Science:

• Cardiovascular Physiology
• Biomedical Engineering
• Data Science

Background:

• Heart rate variability (HRV) is a key indicator for cardiovascular disease risk, traditionally measured via electrocardiography (ECG).
• Photoplethysmography (PPG) offers a more accessible method for collecting heart rate data.
• The clinical utility of PPG-derived HRV for disease prediction remains an active area of research.

Purpose of the Study:

• To investigate the feasibility of estimating HRV from PPG-based heart rate data.
• To assess the potential of PPG-derived HRV for predicting hypertension.
• To identify optimal HRV parameters for early disease detection.

Main Methods:

• Collected three months of PPG-based heart rate data from hypertensive and normotensive subjects.
• Calculated HRV using time and frequency domain analyses.
• Applied data mining techniques with six HRV parameters to predict hypertension.

Main Results:

• Photoplethysmography (PPG) data can be used to accurately estimate heart rate variability (HRV).
• The Standard Deviation of NN intervals (SDNN) demonstrated the highest predictive power for hypertension among the analyzed HRV parameters.
• The study successfully identified patients with hypertension using PPG-derived HRV data.

Conclusions:

• PPG-based heart rate monitoring is a feasible method for estimating HRV.
• Early disease prediction, specifically hypertension, is achievable using readily available PPG data.
• This approach offers a non-invasive and accessible tool for cardiovascular health assessment.