CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks

TL;DR

CovidDeep is a novel framework that leverages wearable medical sensors and efficient neural networks to enable rapid, large-scale, and accurate COVID-19 testing, surpassing traditional methods especially in early detection.

Contribution

The paper introduces CovidDeep, combining wearable sensors with optimized deep neural networks, including synthetic data augmentation and grow-and-prune techniques, to improve COVID-19 detection accuracy and efficiency.

Findings

Achieved up to 98.1% test accuracy in classifying COVID-19 status.

Demonstrated the effectiveness of synthetic data augmentation in improving model performance.

Reduced neural network size and computational complexity without sacrificing accuracy.

Abstract

The novel coronavirus (SARS-CoV-2) has led to a pandemic. The current testing regime based on Reverse Transcription-Polymerase Chain Reaction for SARS-CoV-2 has been unable to keep up with testing demands, and also suffers from a relatively low positive detection rate in the early stages of the resultant COVID-19 disease. Hence, there is a need for an alternative approach for repeated large-scale testing of SARS-CoV-2/COVID-19. We propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus. We collected data from 87 individuals, spanning three cohorts including healthy, asymptomatic, and symptomatic patients. We trained DNNs on various subsets of the features automatically extracted from six WMS and questionnaire categories to perform ablation studies to determine which subsets are most efficacious in terms of test accuracy for a three-way classification. The highest test accuracy obtained was 98.1%. We also augmented the real training dataset with a synthetic training dataset drawn from the same probability distribution to impose a prior on DNN weights and leveraged a grow-and-prune synthesis paradigm to learn both DNN architecture and weights. This boosted the accuracy of the various DNNs further and simultaneously reduced their size and floating-point operations.