Diagnostic performance of deep learning for infectious keratitis: a systematic review and meta-analysis
Year: 2024
Type: review
Study designs: Systematic Review, Meta-Analysis
Abstract: Background: Infectious keratitis (IK) is the leading cause of corneal blindness globally. Deep learning (DL) is an emerging tool for medical diagnosis, though its value in IK is unclear. We aimed to assess the diagnostic accuracy of DL for IK and its comparative accuracy with ophthalmologists. Methods: In this systematic review and meta-analysis, we searched EMBASE, MEDLINE, and clinical registries for studies related to DL for IK published between 1974 and July 16, 2024. We performed meta-analyses using bivariate models to estimate summary sensitivities and specificities. This systematic review was registered with PROSPERO (CRD42022348596). Findings: Of 963 studies identified, 35 studies (136,401 corneal images from >56,011 patients) were included. Most studies had low risk of bias (68.6%) and low applicability concern (91.4%) in all domains of QUADAS-2, except the index test domain. Against the reference standard of expert consensus and/or microbiological results (seven external validation studies; 10,675 images), the summary estimates (95% CI) for sensitivity and specificity of DL for IK were 86.2% (71.6-93.9) and 96.3% (91.5-98.5). From 28 internal validation studies (16,059 images), summary estimates for sensitivity and specificity were 91.6% (86.8-94.8) and 90.7% (84.8-94.5). Based on seven studies (4007 images), DL and ophthalmologists had comparable summary sensitivity [89.2% (82.2-93.6) versus 82.2% (71.5-89.5); P = 0.20] and specificity [(93.2% (85.5-97.0) versus 89.6% (78.8-95.2); P = 0.45]. Interpretation: DL models may have good diagnostic accuracy for IK and comparable performance to ophthalmologists. These findings should be interpreted with caution due to the image-based analysis that did not account for potential correlation within individuals, relatively homogeneous population studies, lack of pre-specification of DL thresholds, and limited external validation. Future studies should improve their reporting, data diversity, external validation, transparency, and explainability to increase the reliability and generalisability of DL models for clinical deployment. Funding: NIH, Wellcome Trust, MRC, Fight for Sight, BHP, and ESCRS.
Source: EClinicalMedicine
Institutions: Birmingham and Midland Eye Centre, University of Birmingham, University of Colorado Anschutz, University Hospitals Birmingham NHS Foundation Trust, Health Data Research UK, Imperial College London, University of Nottingham, Singapore National Eye Center, Singapore Eye Research Institute, Duke-NUS Medical School, Queen's Medical Centre, Moorfields Eye Hospital NHS Foundation Trust, National Institute for Health and Care Research, London School of Hygiene & Tropical Medicine, International Centre for Eye Health, University College London
Language: English
Subfield: Ophthalmology
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $5,000
Awards: G1143353636, Impact of Oral Disulfiram on Aldehyde Dehydrogenase (ALDH) Mediated Ocular Fibrosis in Mucous Membrane Pemphigoid (OcMMP), SEVERE CORNEAL INFECTIONS: PREVENTION, DIAGNOSIS AND TREATMENT, G339059223, Human Hybrid Antimicrobial Peptides for Corneal Infection: From Molecular Dynamic Simulation to In Vivo Animal Studies, Fluid-Gels as Resorbable Protective Dressings for Ocular Surface Disease, Maximizing Use of High-Quality Evidence in Eye Care: Cochrane Eyes and Vision US Project, Determinants of the periocular microbiome
OpenAlex ID: W4403532138