Hypertension Detection From High-Dimensional Representation of Photoplethysmogram Signals

Navid Hasanzadeh; Shahrokh Valaee; Hojjat Salehinejad

Abstract

Hypertension is commonly referred to as ``silent killer", since it can lead to severe health complications without any visible symptoms. Early detection of hypertension is crucial in preventing significant health issues. Although some studies suggest a relationship between blood pressure and certain vital signals, such as Photoplethysmogram (PPG), reliable generalization of the proposed blood pressure estimation methods is not guaranteed yet. This has resulted in some studies doubting the existence of such relationships or considering them weak and limited to heart rate and blood pressure. In this paper, a high-dimensional representation technique based on random convolution kernels is proposed to demonstrate the feasibility of generalization in hypertension detection using PPG signals. Our results provide evidence that this relationship extends beyond heart rate and blood pressure. Additionally, we show that the utilized transform using convolution kernels, as an end-to-end time-series feature extractor method, performs better than the methods proposed in the previous studies and state-of-the-art deep learning models. Clinical relevance- The findings of this study highlight the feasibility of hypertension detection using PPG signals. This could be useful for the early detection of high blood pressure and reducing the risk of hypertension going unnoticed, particularly using wearable devices such as smartwatches equipped with PPG sensors.

Keywords: hypertension; blood pressure; photoplethysmogram (PPG); machine learning; wearable device

Links
[Full text PDF][Bibtex]