PCovNet+: A CNN-VAE anomaly detection framework with LSTM embeddings for smartwatch-based COVID-19 detection

Farhan Fuad Abir; Muhammad E H Chowdhury; Malisha Islam Tapotee; Adam Mushtak; Amith Khandakar; Sakib Mahmud; Md Anwarul Hasan

doi:10.1016/j.engappai.2023.106130

PCovNet+: A CNN-VAE anomaly detection framework with LSTM embeddings for smartwatch-based COVID-19 detection

Eng Appl Artif Intell. 2023 Jun:122:106130. doi: 10.1016/j.engappai.2023.106130. Epub 2023 Mar 28.

Authors

Farhan Fuad Abir¹, Muhammad E H Chowdhury², Malisha Islam Tapotee³, Adam Mushtak⁴, Amith Khandakar², Sakib Mahmud², Md Anwarul Hasan⁵

Affiliations

¹ Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, United States.
² Department of Electrical Engineering, Qatar University, Doha 2713, Qatar.
³ Department of Electrical and Electronic Engineering, University of Dhaka, Dhaka 1000, Bangladesh.
⁴ Clinical Imaging Department, Hamad Medical Corporation, Doha, Qatar.
⁵ Department of Mechanical and Industrial Engineering, Qatar University, Doha 2713, Qatar.

Abstract

The world is slowly recovering from the Coronavirus disease 2019 (COVID-19) pandemic; however, humanity has experienced one of its According to work by Mishra et al. (2020), the study's first phase included a cohort of 5,262 subjects, with 3,325 Fitbit users constituting the majority. However, among this large cohort of 5,262 subjects, most significant trials in modern times only to learn about its lack of preparedness in the face of a highly contagious pathogen. To better prepare the world for any new mutation of the same pathogen or the newer ones, technological development in the healthcare system is a must. Hence, in this work, PCovNet+, a deep learning framework, was proposed for smartwatches and fitness trackers to monitor the user's Resting Heart Rate (RHR) for the infection-induced anomaly. A convolutional neural network (CNN)-based variational autoencoder (VAE) architecture was used as the primary model along with a long short-term memory (LSTM) network to create latent space embeddings for the VAE. Moreover, the framework employed pre-training using normal data from healthy subjects to circumvent the data shortage problem in the personalized models. This framework was validated on a dataset of 68 COVID-19-infected subjects, resulting in anomalous RHR detection with precision, recall, F-beta, and F-1 score of 0.993, 0.534, 0.9849, and 0.6932, respectively, which is a significant improvement compared to the literature. Furthermore, the PCovNet+ framework successfully detected COVID-19 infection for 74% of the subjects (47% presymptomatic and 27% post-symptomatic detection). The results prove the usability of such a system as a secondary diagnostic tool enabling continuous health monitoring and contact tracing.

Keywords: Anomaly detection; COVID-19; Convolutional neural network; Long short-term memory; Resting heart rate; Variational autoencoder; Wearables.