Normalization of photoplethysmography using deep neural networks for individual and group comparison.

Photoplethysmography (PPG) is easy to measure and provides important parameters related to heart rate and arrhythmia. However, automated PPG methods have not been developed because of their susceptibility to motion artifacts and differences in waveform characteristics among individuals. With increasing use of telemedicine, there is growing interest in application of deep neural network (DNN) technology for efficient analysis of vast amounts of PPG data. This study is about an algorithm for measuring a patient's PPG and comparing it with their own data stored previously and with the average data of several groups. Six deep neural networks were used to normalize the PPG waveform according to the heart rate by removing uninformative regions from the PPG, distinguishing between heartbeat and reflection pulses, dividing the heartbeat waveform into 10 segments and averaging the values according to each segments. PPG data were measured using telemedicine in both groups. Group 1 consisted of healthy people aged 25 to 35 years, and Group 2 consisted of patients between 60 and 75 years of age taking antihypertensive medications. The proposed algorithm could accurately determine which group the subject belonged with the newly measured PPG data (AUC = 0.998). On the other hand, errors were frequently observed in identification of individuals (AUC = 0.819).