Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Feb 8, 2023
Open Peer Review Period: Feb 7, 2023 - Feb 24, 2023
Date Accepted: Jun 30, 2023
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Diagnostic test accuracy of deep learning prediction models on COVID-19 severity: a systematic review and meta-analysis
ABSTRACT
Background:
Deep learning (DL) prediction models hold significant promise in the triage of coronavirus disease 2019 (COVID-19).
Objective:
We aimed to evaluate the diagnostic test accuracy (DTA) of DL prediction models for assessment and prediction of COVID-19 severity.
Methods:
We searched PubMed, Scopus, LitCovid, Embase, Ovid, and Cochrane Library for studies published from December 1, 2019, to April 30, 2022. Studies that used DL prediction models to assess or predict COVID-19 severity were included, while those without DTA analysis or severity dichotomies were excluded. QUADAS-2, PROBAST, and funnel plots were used to estimate the bias and applicability.
Results:
Twelve retrospective studies involving 2006 patients reported the cross-sectionally assessed value of DL on COVID-19 severity. The pooled sensitivity (SEN), and area under curve (AUC) were 0·92 (95% CI 0·89–0·94, I2 = 0·00%), and 0·95 (95% CI 0·92–0·96). Thirteen retrospective studies involving 3951 patients reported the longitudinally predictive value of DL on disease severity. The pooled SEN, and AUC were 0·76 (95% CI 0·74–0·79, I2 = 0·00%), and 0·80 (95% CI 0·76–0·83).
Conclusions:
DL prediction models can help clinicians identify potentially severe cases to triage early. However, there is a lack of high-quality research. Clinical Trial: PROSPERO number: CRD42022329252
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.