Teledermatology Diagnostic Accuracy: A Randomized Cohort Study Comparing Three Image Acquisition Techniques

Teledermatology is increasingly recognized as a valuable tool for expanding access to dermatologic care, particularly in underserved and remote settings. This randomized prospective cohort study, the first of its kind in the region, examined the diagnostic and treatment concordance of teledermatologists compared to in-clinic dermatologists, with a focus on the impact of image acquisition methods. A total of 360 adult patients presenting for dermatologic evaluation at the American University of Beirut Medical Center were enrolled. Each patient contributed three sets of skin lesion photographs: unassisted patient-taken, assisted patient-taken after brief standardized training, and resident-taken under clinical conditions. Using a store-and-forward model, teledermatologists reviewed one randomized image set per patient. Their diagnoses and treatment decisions were compared to in-person assessments, which served as the reference standard. Diagnostic concordance improved with image quality: 79% for unassisted patient images, 84% for assisted images, and 87% for resident-taken images. Treatment concordance similarly increased from 38% to 44% to 45%, while the need to request additional history declined from 64% to 47%. Acne showed the highest diagnostic match across all image types. These findings support the clinical validity of store-and-forward teledermatology and highlight the value of patient education in improving image quality and diagnostic outcomes. As the first regional study to systematically evaluate real-world image acquisition methods, it offers a practical roadmap for integrating teledermatology into routine dermatologic care.