We are incredibly proud to announce that our paper on CovidDeep is now the most popular in IEEE Transactions on Consumer Electronics.
CovidDeep is a framework called that combines efficient deep neural networks (DNN)s with commercially available wearable medical sensors for pervasive testing of the COVID-19 virus and the resultant disease.
Here is the abstract. The CovidDeep paper can be found on IEEE Transactions on Consumer Electronics‘ website.
Read the CovidDeep case study.
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. The emergence of wearable medical sensors (WMSs) and deep neural networks (DNNs) points to a promising approach to address this challenge.
WMSs enable continuous and user-transparent monitoring of physiological signals. However, disease detection based on WMSs/DNNs and their deployment on resource-constrained edge devices remain challenging problems. To address these problems, we propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus and the resultant disease. CovidDeep does not depend on manual feature extraction. It directly operates on WMS data and some easy-to-answer questions in a questionnaire whose answers can be obtained through a smartphone application.
We collected data from 87 individuals, spanning three cohorts, including healthy, asymptomatic (to detect the virus), and symptomatic (to detect the disease) 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%. The models were also shown to perform well on other performance measures, such as false-positive rate, false-negative rate, and F1 score.
We 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. This makes the CovidDeep DNNs both accurate and efficient in terms of memory requirements and computations. The resultant DNNs are embedded in a smartphone application, which has the added benefit of preserving patient privacy.