Classification Of Hypertension Using K-Nearest Neighbor Based On Photoplethysmograph Data And Blood Pressure Estimator

Abstract

Hypertension is a persistent cardiovascular condition, often termed the “silent killer” because it typically presents no symptoms in its early stages. To address the shortcomings of traditional blood pressure monitoring methods, this study develops a classification system that leverages photoplethysmography (PPG) signals in combination with the K-Nearest Neighbor (KNN) algorithm. PPG provides a promising non-invasive solution that is readily adaptable to portable devices. The classification process employs the Euclidean Distance method to determine the similarity between new data samples and previously labeled instances. Data were collected from 276 individuals spanning various age groups using PPG sensors connected to the MR-IAT Robot Covid platform. The system categorizes individuals into normotensive, prehypertensive, stage 1, and stage 2 hypertension groups. The study evaluates the performance of the KNN algorithm based on its ability to predict blood pressure categories from morphological features extracted from the PPG signals. Ultimately, the outcomes of this research are expected to advance the development of efficient, real-time, continuous blood pressure monitoring systems through user-friendly machine learning approaches.