Artificial intelligence model on chest imaging to diagnose COVID-19 and other pneumonias: A systematic review and meta-analysis.

Objectives: When diagnosing Coronavirus disease 2019(COVID-19), radiologists cannot make an accurate judgments because the image characteristics of COVID-19 and other pneumonia are similar. As machine learning advances, artificial intelligence(AI) models show promise in diagnosing COVID-19 and other pneumonias. We performed a systematic review and meta-analysis to assess the diagnostic accuracy and methodological quality of the models.

Methods: We searched PubMed, Cochrane Library, Web of Science, and Embase, preprints from medRxiv and bioRxiv to locate studies published before December 2021, with no language restrictions. And a quality assessment (QUADAS-2), Radiomics Quality Score (RQS) tools and CLAIM checklist were used to assess the quality of each study. We used random-effects models to calculate pooled sensitivity and specificity, I values to assess heterogeneity, and Deeks' test to assess publication bias.

Results: We screened 32 studies from the 2001 retrieved articles for inclusion in the meta-analysis. We included 6737 participants in the test or validation group. The meta-analysis revealed that AI models based on chest imaging distinguishes COVID-19 from other pneumonias: pooled area under the curve (AUC) 0.96 (95 % CI, 0.94-0.98), sensitivity 0.92 (95 % CI, 0.88-0.94), pooled specificity 0.91 (95 % CI, 0.87-0.93). The average RQS score of 13 studies using radiomics was 7.8, accounting for 22 % of the total score. The 19 studies using deep learning methods had an average CLAIM score of 20, slightly less than half (48.24 %) the ideal score of 42.00.

Conclusions: The AI model for chest imaging could well diagnose COVID-19 and other pneumonias. However, it has not been implemented as a clinical decision-making tool. Future researchers should pay more attention to the quality of research methodology and further improve the generalizability of the developed predictive models.