Predicting blood pressure from face videos using face diagnosis theory and deep neural networks technique

Hypertension is a major cause of cardiovascular diseases. Accurate and convenient measurement of blood pressure are necessary for the detection, treatment, and control of hypertension. In recent years, face video based non-contact blood pressure prediction is a promising research topic. Interestingly, face diagnosis has been an important part of traditional Chinese medicine (TCM) for thousands of years. TCM practitioners observe some typical regions of the face to determine the health status of the Zang Fu organs (i.e., heart). However, the effectiveness of face diagnosis theory in conjunction with computer vision analysis techniques to predict blood pressure is unclear. We proposed an artificial intelligence framework for predicting blood pressure using deep convolutional neural networks in this study. First, we extracted pulse wave signals through 652 facial videos. Then, we trained and compared nine artificial neural networks and chose the best performed prediction model, with an overall true predict rate of 90%. We also investigated the impact of face reflex regions selection on blood pressure prediction model, and the five face regions outperformed. Our high effectiveness and stability framework may provide an objective and convenient computer-aided blood pressure prediction method for hypertension screening and disease prevention.