Classification of Hypertension Levels Based on Photoplethysmography Signals Using Convolutional Neural Network (CNN)

Hypertension is a serious medical condition that has the potential to elevate the risk of diseases affecting various organs. According to statistical data from the World Health Organization (WHO), in 2019, cardiovascular diseases such as heart, brain, kidney, and other organ diseases have significantly increased due to hypertension, affecting approximately 1.4 billion people worldwide. Blood pressure monitoring is needed to reduce the risk, considering other parameters such as gender, age, height, weight, heart rate, and Body Mass Index (BMI). In blood pressure monitoring, many recent studies have used Photoplethysmography (PPG) signal for blood pressure measurement due to its easy-to-obtain and more accurate measurement. In this research, we will employ a Convolutional Neural Network (CNN) to analyze PPG signal characteristics and make predictions for both Systolic Blood Pressure (SBP) and Diastolic Blood Pressure (DBP). Additionally, a CNN architecture will be harnessed to categorize hypertension levels based on the forecasted blood pressure, as well as various factors such as gender, age, height, weight, heart rate, and BMI. This investigation will categorize hypertension into Pre-Hypertension, Normal, Hypertension Stage 1, and Hypertension Stage 2, utilizing a dataset consisting of 219 patients data and 657 PPG signal recordings. Using the proposed method, hypertension classification using CNN with classification report: accuracy 95%, F1-score 94,6%, recall 94,6%, precision 95.1%. The result shows that the proposed method is a promising solution to classify hypertension based on the Photoplethysmography signal effectively. This method can assist medical professionals in making clinical diagnoses with greater accuracy.