Data-knowledge co-driven feature based prediction model via photoplethysmography for evaluating blood pressure

Knowledge feature (KF) with clear physiological significance of photoplethysmography are widely used in predicting blood pressure. However, KF primarily focus on local information of photoplethysmography, which may struggle to capture the overall characteristics. Firstly, functional data analysis (FDA) was introduced to extract two types of data feature (DF). Furthermore, data-knowledge co-driven feature (DKCF) was proposed by combining FDA and constraints of KF. Finally, random forest, ada boost, gradient boosting, support vector machine and deep neural network were adopted, to compare the abilities of KF, DFs and DKCF in predicting blood pressure with two datasets (A published dataset and a self-collected dataset). Under the premise of extracting only 9 features, the average mean absolute errors (MAE) of systolic blood pressure (SBP) and diastolic blood pressure (DBP) obtained by DKCF are both the smallest in dataset 1. In dataset 2, DKCF acquires the smallest MAE in predicting SBP and obtains the second smallest MAE in predicting DBP. The results demonstrate that low-dimensional DKCF of photoplethysmography is closely correlated with blood pressure, which may serve as an important indicator for health assessment. [Display omitted] •Extracting geometric features from PPG signals based on functional data analysis (FDA) methods.•Proposing data-knowledge co-driven feature (DKCF) by combining knowledge feature (KF) and FDA methods.•DKCF is a low dimensional feature that considers both physiological significance and geometric characteristics.