ENHANCED HYPERTENSION CLASSIFIER BASED ON PHOTOPLETHYSMOGRAM SIGNAL USING STATISTICAL ANALYSIS AND EXTREME LEARNING MACHINE METHOD

Hypertension prevalence is known to increase with urbanization and ageing population. The combination of urbanization and ageing can have a compounding effect on the prevalence of hypertension. As populations age in urban areas, there is a higher risk of developing hypertension due to both lifestyle factors and physiological changes. This has significant public health implications, as hypertension is a major risk factor for cardiovascular disease, stroke, and kidney disease. The aim of this study is establishing an operator independent screening technique with reliable accuracy in classifying hypertensive subjects using finger photoplethysmogram signal. In achieving the targeted classifier, a hybrid methodology was used in PPG signal processing and analysis. Signal processing includes denoising and conditioning the signal to increase the reliability of the extracted features. The extracted PPG feature was analysed using computation of statistical features skewness. The analysis output features were classified using Extreme Learning Machine (ELM) a high-dimensional feature spaces classifier. Three different combinations were tested namely, skewness, peak and a combination of both. The data classification was tested in three different models to compare its accuracy (10 layers: 81.18%; 1000 layers: 89.665; 1500 layers: 91.46%). A significant difference in accuracy between the training and testing data was observed, it is estimated to be due to the small sample size. The advantage of the proposed model is its ability to produce higher accuracy with smaller data set, which is a significant contribution for underdeveloped and developing countries where they are yet to build and establish their healthcare repositories.