PCovNet: A presymptomatic COVID-19 detection framework using deep learning model using wearables data

• Published in: Computers in Biology and Medicine Vol. 147; p. 105682
• Main Authors: Abir, Farhan Fuad, Alyafei, Khalid, Chowdhury, Muhammad E.H., Khandakar, Amith, Ahmed, Rashid, Hossain, Muhammad Maqsud, Mahmud, Sakib, Rahman, Ashiqur, Abbas, Tareq O., Zughaier, Susu M., Naji, Khalid Kamal
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.08.2022; Elsevier BV; Elsevier Limited
• Subjects: Anomalies; Anomaly detection; Asymptomatic; Configurations; Contact tracing; Coronaviruses; COVID-19; COVID-19 - diagnosis; COVID-19 diagnostic tests; COVID-19 Testing; Datasets; Deep Learning; Diagnosis; Disease transmission; Heart rate; Humans; Infections; Internal Medicine; Long short-term memory; Medical research; Monitoring systems; Other; Pandemics; Pathogens; Polymerase chain reaction; Presymptomatic; Respiratory diseases; Resting heart rate; Reverse transcription; SARS-CoV-2; Sensors; Severe acute respiratory syndrome coronavirus 2; Sleep; Smartwatch; Smartwatches; Swine flu; Teaching methods; Tracking devices; Variational autoencoder; Viral diseases; Wearable computers; Wearable Electronic Devices; Wearable technology; COVID-19; Presymptomatic; Resting heart rate; Long short-term memory; Variational autoencoder; Smartwatch; Anomaly detection
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105682

While the advanced diagnostic tools and healthcare management protocols have been struggling to contain the COVID-19 pandemic, the spread of the contagious viral pathogen before the symptom onset acted as the Achilles’ heel. Although reverse transcription-polymerase chain reaction (RT-PCR) has been widely used for COVID-19 diagnosis, they are hardly administered before any visible symptom, which provokes rapid transmission. This study proposes PCovNet, a Long Short-term Memory Variational Autoencoder (LSTM-VAE)-based anomaly detection framework, to detect COVID-19 infection in the presymptomatic stage from the Resting Heart Rate (RHR) derived from the wearable devices, i.e., smartwatch or fitness tracker. The framework was trained and evaluated in two configurations on a publicly available wearable device dataset consisting of 25 COVID-positive individuals in the span of four months including their COVID-19 infection phase. The first configuration of the framework detected RHR abnormality with average Precision, Recall, and F-beta scores of 0.946, 0.234, and 0.918, respectively. However, the second configuration detected aberrant RHR in 100% of the subjects (25 out of 25) during the infectious period. Moreover, 80% of the subjects (20 out of 25) were detected during the presymptomatic stage. These findings prove the feasibility of using wearable devices with such a deep learning framework as a secondary diagnosis tool to circumvent the presymptomatic COVID-19 detection problem. •A wearable device-based presymptomatic COVID-19 detection framework was proposed.•Resting Heart Rate (RHR) was calculated from heart rate and steps data.•An LSTM Variational Autoencoder-based framework with two separate configurations was proposed for detecting anomalous RHR.•Smartwatch-based RHR monitoring system as a secondary diagnostic tool was validated for continuous health monitoring.