Continuous blood pressure estimation using ECG and PPG in the operating theatre

In a significant portion of surgeries, blood pressure (BP) is often measured non-invasively in an intermittent manner. This practice has a risk of missing clinically-relevant BP changes between two adjacent intermittent BP measurements. This study proposes a method to continuously estimate systolic blood pressure (SBP) based on previous intermittent SBP measurements and electrocardiography (ECG) and photoplethysmography (PPG) derived features. Continuous ABP, ECG, and PPG signals were acquired from 23 patients undergoing major surgery. After extracting nine features from PPG and ECG signals, we dynamically selected features upon each intermittent measurement (every 10 minutes) of SBP based on feature robustness and the principle of correlation feature selection. Finally, a multiple linear regression model was built to combine these features in order to estimate SBP every 30 seconds. Compared to reference SBP, the proposed method achieved a mean of difference at 0.07 mmHg, a standard deviation of difference at 7.92 mmHg, and a correlation coefficient at 0.89. This study presents the feasibility of continuously estimating SBP with clinically-acceptable accuracy during surgery with the aid of non-invasive intermittent BP measurements.