Diagnostic accuracy of teledermatology for skin diseases: a systematic review and meta-analysis

Background: Skin diseases affect nearly one-third of the global population, yet limited access to dermatological care remains an unmet challenge. Teledermatology offers a promising solution, however, concerns about technological and workforce demands have limited its broader adoption. Furthermore, its diagnostic reliability across communication platforms and types, and different skin conditions remains unclear. Objectives: We aimed to evaluate the diagnostic accuracy of teledermatology compared to in-person consultations. Methods: We searched PubMed, Embase, and CENTRAL on November 19, 2023, for observational and experimental studies, without date or language restrictions. Primary outcomes included diagnostic concordance, Cohen's kappa, sensitivity, specificity, and predictive values; secondary outcomes were diagnostic time, teledermatology provider and patient satisfaction and interrater agreement. A random intercept logistic regression model was used to pool outcomes. Subgroup analyses were conducted by disease category, communication platform (store-and-forward, real-time, hybrid), type (indirect, direct), dermoscopy use, photography device, and training. Results: Out of 30,412 records, 155 studies were included, with 139 analyzed quantitatively. Diagnostic concordance was 76% in all skin conditions (95%-CI: 73-79%), 73% in skin cancers (95%-CI: 67-79%) and 76% in pigmented lesions (95%-CI: 67-83%). Use of dermoscopy significantly improved diagnostic concordance from 67% (95%-CI: 58-74%) to 80% (95%-CI, 73-85%) in skin cancers. No significant differences were found by communication type, platform, or photography device. The mean diagnostic time was 1.05 min per case (95%-CI, 0.98-1.12). Patient satisfaction was high (82%, 95%-CI: 76-87%). Conclusion: Teledermatology demonstrates high diagnostic accuracy, supporting its use as a reliable alternative to in-person care for diagnosing general skin conditions and screening for skin cancer. Given its broad applicability, teledermatology stands out as a potential tool to improve access to dermatological care. Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD42023484476, identifier CRD42023484476.