Res-SE-ConvNet: A Deep Neural Network for Hypoxemia Severity Prediction for Hospital In-Patients Using Photoplethysmograph Signal
Official repository for the paper "Res-SE-ConvNet: A Deep Neural Network for Hypoxemia Severity Prediction for Hospital In-Patients Using Photoplethysmograph Signal". Please run pip3 install -r requirements.txt in a Python environment and then run train.py.
Dataset:
Abstract: Determining the severity level of hypoxemia, the scarcity of saturated oxygen (SpO2) in the human body, is very important for the patients, a matter which has become even more significant during the outbreak of Covid-19 variants. Although the widespread usage of Pulse Oximeter has helped the doctors aware of the current level of SpO2 and thereby determine the hypoxemia severity of a particular patient, the high sensitivity of the device can lead to the desensitization of the care-givers, resulting in slower response to actual hypoxemia event. There has been research conducted for the detection of severity level using various parameters and bio-signals and feeding them in a machine learning algorithm. However, in this paper, we have proposed a new residual-squeeze-excitation-attention based convolutional network (Res-SE-ConvNet) using only Photoplethysmography (PPG) signal for the comfortability of the patient. Unlike the other methods, the proposed method has outperformed the standard state-of-art methods as the result shows 96.5% accuracy in determining 3 class severity problems with 0.79 Cohen Kappa score. This method has the potential to aid the patients in receiving the benefit of an automatic and faster clinical decision support system, thus handling the severity of hypoxemia.
@ARTICLE{9930756,
author={Mahmud, Talha Ibn and Imran, Sheikh Asif and Shahnaz, Celia},
journal={IEEE Journal of Translational Engineering in Health and Medicine},
title={Res-SE-ConvNet: A Deep Neural Network for Hypoxemia Severity Prediction for Hospital In-Patients Using Photoplethysmograph Signal},
year={2022},
volume={10},
number={},
pages={1-9},
doi={10.1109/JTEHM.2022.3217428}}