In JMIR medical informatics ; h5-index 23.0
BACKGROUND : The Coronavirus Disease 2019 (COVID-2019) outbreak has spread rapidly and hospitals are overwhelmed with COVID-19 patients. While using swabs from patients is the main way for detecting coronavirus, analyzing chest images could offer an alternative to hospitals where healthcare personnel and testing kits are scarce. Deep learning, in particular, has shown impressive performances for analyzing medical images including COVID-19 pneumonia.
OBJECTIVE : To perform a systematic review with a meta-analysis of relevant studies to quantify the performance of the DL algorithms for automatic stratification of COVID-19 using chest images.
METHODS : A search strategy for use of PubMed, Scopus, Google Scholar, and Web of Science was developed (between January 1, 2020, and April 25) using the key terms COVID-19, coronavirus, SARS-CoV-2, novel corona, 2019-ncov and deep learning. Two authors independently extracted data on study characteristics, methods, risk of bias, and outcomes. Any disagreement between them was resolved by consensus.
RESULTS : Sixteen studies were included in the meta-analysis, including 5,896 chest images of COVID-19. The pooled sensitivity and specificity of DL for detecting COVID-19 was 0.95 (95%CI: 0.94-0.95), and 0.96 (95%CI: 0.96-0.97), respectively, with an AUROC of 0.98. The positive likelihood, negative likelihood, and diagnostic odds ratio were 19.02 (12.83-28.19), 0.06(95%CI:0.04-0.10), and 368.07 (95%CI: 162.30-834.75), respectively. The pooled sensitivity and specificity for detecting Pneumonia was 0.93 (95%CI:0.92-0.94), and 0.95(95%CI: 0.94-0.95). The performance of radiologists for detecting COVID-19 was lower than DL; however, the performance of junior radiologists was improved when they used DL-based prediction tools.
CONCLUSIONS : Our study findings show that deep learning models have immense potential accurately stratified COVID-19, and correctly differentiate from other pneumonia and normal patients. Implementation of deep learning-based tools can assist radiologists to correctly and quickly detect COVID-19 and to combat the COVID-19 pandemic.
CLINICALTRIAL : N/a.
Poly Tahmina Nasrin, Islam Md Mohaimenul, Alsinglawi Belal, Hsu Min-Huei, Jian Wen Shan, Yang Hsuan-Chia, Li Yu-Chuan Jack