Neural Network Model Combination for Video-Based Blood Pressure Estimation: New Approach and Evaluation

Abstract

One of the most effective vital signs of health conditions is blood pressure. It has such an impact that changes your state from completely relaxed to extremely unpleasant, which makes the task of blood pressure monitoring a main procedure that almost everyone undergoes whenever there is something wrong or suspicious with his/her health condition. The most popular and accurate ways to measure blood pressure are cuff-based, inconvenient, and pricey, but on the bright side, many experimental studies prove that changes in the color intensities of the RGB channels represent variation in the blood that flows beneath the skin, which is strongly related to blood pressure; hence, we present a novel approach to blood pressure estimation based on the analysis of human face video using hybrid deep learning models. We deeply analyzed proposed approaches and methods to develop combinations of state-of-the-art models that were validated by their testing results on the Vision for Vitals (V4V) dataset compared to the performance of other available proposed models. Additionally, we came up with a new metric to evaluate the performance of our models using Pearson’s correlation coefficient between the predicted blood pressure of the subjects and their respiratory rate at each minute, which is provided by our own dataset that includes 60 videos of operators working on personal computers for almost 20 min in each video. Our method provides a cuff-less, fast, and comfortable way to estimate blood pressure with no need for any equipment except the camera of your smartphone.

Revolutionizing Cardiology through Artificial Intelligence—Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment—A Comprehensive Review of the Past 5 Years

“…Artificial intelligence is increasingly being used in treating hypertension. In the highly scientific literature, numerous machine learning techniques are used to diagnose and detect numerous diseases: hypertension prevention [ 138 ], hypertension prediction [ 132 , 137 , 140 , 142 ], hypertension prediction in young patients [ 133 ], hypertension diagnosis [ 131 , 136 ], hypertension management and treatment [ 134 , 139 , 141 ], and hypertension variability [ 135 ]. Hypertension is found in 1.28 billion adults according to the World Health Organization (WHO).…”

Psychological and Neurophysiological Screening Investigation of the Collective and Personal Stress Resilience

“…This includes both traditional psychological testing, as well as complex registration of a number of parameters—EEG, event-related potentials, ECG, EMG, fMRI, respiratory and vegetative parameters that characterize physical, mental (including cognitive) and professional health [ 1 , 2 , 3 , 4 ]. Recently, approaches utilizing the modeling of virtual reality and neural networks have been developed [ 5 , 6 ]. All of the above is undoubtedly of scientific interest.…”

“…It is believed that artificial intelligence (AI) technologies being created should improve social relations and progress in professional activities [ 6 , 18 , 20 ]. However, research shows that AI can create a number of ethical decision-making issues that contribute to the formation of stress.…”

“…Of course, these factors can be listed further. More importantly, we see the association of known factors with the emergence of new conditions and technologies [ 3 , 5 , 6 ].…”

“…At the same time, the creation of new assessment methods is accompanied by traditional research. In particular, modern methods of artificial intelligence make it possible to solve the problem of classifying states and human behavioral activity based on the analysis of external features obtained during the process of analyzing images from a video camera (including a smartphone) and forming conclusions about its internal state [ 5 , 6 ]. However, to prove these findings, I plan to perform interdisciplinary research in the fields of experimental neurophysiology, psychology, data mining, computer vision, ontological modeling, profiling and recommender systems.…”