Jose Ignacio Rodriguez-Labra,Christopher J. Kosik,Dinesh Maddipatla,Binu B. Narakathu,Massood Z. Atashbar
出处
期刊:IEEE Sensors Journal [Institute of Electrical and Electronics Engineers] 日期:2021-03-08卷期号:21 (23): 26320-26327被引量:29
标识
DOI:10.1109/jsen.2021.3064219
摘要
Wearable devices with integrated sensors for tracking human vitals are widely used for a variety of applications, including exercise, wellness, and health monitoring. Photoplethysmography (PPG) sensors use pulse oximetry to measure pulse rate, cardiac cycle, oxygen saturation, and blood flow by passing a light beam of variable wavelength through the skin and measuring its reflection. A multi-channel PPG wearable system was developed to include multiple nodes of pulse oximeters, each capable of using different wavelengths of light. The system uses sensor fusion along with machine learning model to perform feature extraction of relevant cardiovascular metrics across multiple pulse oximeters and predict saturated oxygen (SpO 2 ). The developed model predicted SpO 2 with a root mean square (RMSE) of 0.07 and accuracy of 99.5%. The wearable system was applied to the plant of the foot for vascular assessment. Wearable PPG systems capable of sensor fusion demonstrates a potential capability for continuous evaluation/monitoring of wounds and diseases associated with abnormal blood flow.