Pulse transit time estimation of aortic pulse wave velocity and blood pressure using machine learning and simulated training data

• Published in: PLoS computational biology Vol. 15; no. 8; p. e1007259
• Main Authors: Huttunen, Janne M. J., Kärkkäinen, Leo, Lindholm, Harri
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 15.08.2019; Public Library of Science (PLoS)
• Subjects: Accuracy; Aorta; Aorta - physiology; Aortic valve; Artificial intelligence; Biology and Life Sciences; Blood flow; Blood Flow Velocity - physiology; Blood pressure; Blood Pressure - physiology; Blood pressure measurement; Carotid artery; Computational Biology; Computer applications; Computer Simulation; Coronary vessels; Data collection; Databases, Factual; Feet; Gaussian process; Heart; Heart rate; Humans; Laboratories; Learning algorithms; Machine Learning; Medical examination; Medicine and Health Sciences; Methods; Models, Cardiovascular; Normal Distribution; Patient simulation; Photoplethysmography - statistics & numerical data; Propagation; Pulse diagnosis; Pulse Wave Analysis - statistics & numerical data; Signal processing; Statistics; Stroke; Stroke volume; Stroke Volume - physiology; Technology application; Transit time; Ultrasonic imaging; User-Computer Interface; Vascular Stiffness; Veins & arteries; Velocity; Wave velocity; Wearable Electronic Devices - statistics & numerical data; Finland
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1007259

Recent developments in cardiovascular modelling allow us to simulate blood flow in an entire human body. Such model can also be used to create databases of virtual subjects, with sizes limited only by computational resources. In this work, we study if it is possible to estimate cardiovascular health indices using machine learning approaches. In particular, we carry out theoretical assessment of estimating aortic pulse wave velocity, diastolic and systolic blood pressure and stroke volume using pulse transit/arrival timings derived from photopletyshmography signals. For predictions, we train Gaussian process regression using a database of virtual subjects generated with a cardiovascular simulator. Simulated results provides theoretical assessment of accuracy for predictions of the health indices. For instance, aortic pulse wave velocity can be estimated with a high accuracy (r > 0.9) when photopletyshmography is measured from left carotid artery using a combination of foot-to-foot pulse transmit time and peak location derived for the predictions. Similar accuracy can be reached for diastolic blood pressure, but predictions of systolic blood pressure are less accurate (r > 0.75) and the stroke volume predictions are mostly contributed by heart rate.