Optimizing The Input Feature Sets And Machine Learning Algorithms For Reliable And Accurate Estimation Of Continuous, Cuffless Blood Pressure

This article discusses the need for accurate, reliable, and non-invasive ways to measure continuous blood pressure (BP). It demonstrates how multimodal feature datasets, comprising pulse arrival time (PAT), pulse wave morphology (PWM), and demographic data, can be combined with optimized Machine Learning (ML) algorithms to estimate Systolic BP (SBP), Diastolic BP (DBP) and Mean Arterial Pressure (MAP) within a 5 mmHg bias of the gold standard Intra-Arterial BP. ANOVA and Levene’s test for error means and standard deviations were used to find significant differences in the various ML algorithms but found no significant differences amongst the multimodal feature datasets.