Assessing diagnostic performance for common skin diseases using an AI-assisted tele-expertise platform: a proof of concept
Abstract
Advancements in machine learning (ML) are making artificial intelligence more feasible in dermatology, with promising results for diagnosing skin cancers, though few studies cover common or inflammatory dermatoses. To evaluate the diagnostic accuracy for common non-cancerous skin diseases and the clinical applicability of an ML model in practical telemedicine. A prospective, multi-centre, diagnostic accuracy study including patients with common dermatoses, between October 2022 and July 2023, was performed. The top three diagnoses (Top 1, Top 2 and Top 3) from the AI system, trained to recognize 25 common dermatoses based on skin lesion images and medical data, were compared to diagnoses by two dermatologists (gold standard) to calculate the AI model's diagnostic accuracy, sensitivity, and specificity. Two versions of the AI software were evaluated: version 1 (V1) and version 2 (V2) with and without medical supervision (MS), referring to the use of metadata to control diagnostic predictions. Seventy participants and 195 photographs were included. The sensitivity and specificity of the Top 3 algorithm were 88% and 90%, respectively, for V2, with a significant improvement compared with V1. For V1, diagnostic accuracy was 0.57 (0.46;0.69) for Top 1, 0.70 (0.59;0.81) for Top 2, and 0.81 (0.72;0.91) for Top 3. For V2, diagnostic accuracy was 0.69 (0.58;0.79) and 0.71 (0.61;0.82) without and with MS, respectively, for Top 1; 0.87 (0.79;0.95) for Top 2; and 0.90 (0.83;0.97) for Top 3. Our AI model appears to be a promising tool for triaging and diagnosing skin lesions, especially for non-specialist physicians.
Related
- Diagnostic Performance of Corrected Carotid Flow Time for Assessing Fluid Responsiveness in Patients With Septic or Hypovolemic Shock: A Prospective Diagnostic Accuracy Study
- Diagnostic performance of liver biochemical and hemostatic markers for assessing cirrhosis severity in chronic hepatitis B
- Reproducibility and diagnostic performance of ADC for assessing response to neoadjuvant immunotherapy in muscle-invasive bladder cancer: a multi-ROI comparison analysis from the phase-Ib NABUCCO trial
- Clinical expertise and cognitive reflection predict fewer misconceptions in Bayesian diagnostic reasoning
- Trust in AI-Assisted Medical Expertise Among Patients with Diabetes: A Qualitative Focus Group Study
BibTeX
@article{lay2026assessing,
title = {{Assessing diagnostic performance for common skin diseases using an AI-assisted tele-expertise platform: a proof of concept}},
author = {Florine Le Lay and Ouriel Barzilay and Damiano Cerasuolo and Hélène Roger and Rachel Abergel and Marie Jouandet and Priscille Carvalho-Lallement and Anne Dompmartin and Jean-Matthieu L’orphelin},
journal = {European Journal of Dermatology},
year = {2026},
month = sep,
doi = {10.1684/ejd.2024.4804},
url = {https://hal.science/hal-05746065v1},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Assessing diagnostic performance for common skin diseases using an AI-assisted tele-expertise platform: a proof of concept
AU - Florine Le Lay
AU - Ouriel Barzilay
AU - Damiano Cerasuolo
AU - Hélène Roger
AU - Rachel Abergel
AU - Marie Jouandet
AU - Priscille Carvalho-Lallement
AU - Anne Dompmartin
AU - Jean-Matthieu L’orphelin
PY - 2026
DA - 2026/09/10
JO - European Journal of Dermatology
DO - 10.1684/ejd.2024.4804
UR - https://hal.science/hal-05746065v1
AB - Advancements in machine learning (ML) are making artificial intelligence more feasible in dermatology, with promising results for diagnosing skin cancers, though few studies cover common or inflammatory dermatoses. To evaluate the diagnostic accuracy for common non-cancerous skin diseases and the clinical applicability of an ML model in practical telemedicine. A prospective, multi-centre, diagnostic accuracy study including patients with common dermatoses, between October 2022 and July 2023, was performed. The top three diagnoses (Top 1, Top 2 and Top 3) from the AI system, trained to recognize 25 common dermatoses based on skin lesion images and medical data, were compared to diagnoses by two dermatologists (gold standard) to calculate the AI model's diagnostic accuracy, sensitivity, and specificity. Two versions of the AI software were evaluated: version 1 (V1) and version 2 (V2) with and without medical supervision (MS), referring to the use of metadata to control diagnostic predictions. Seventy participants and 195 photographs were included. The sensitivity and specificity of the Top 3 algorithm were 88% and 90%, respectively, for V2, with a significant improvement compared with V1. For V1, diagnostic accuracy was 0.57 (0.46;0.69) for Top 1, 0.70 (0.59;0.81) for Top 2, and 0.81 (0.72;0.91) for Top 3. For V2, diagnostic accuracy was 0.69 (0.58;0.79) and 0.71 (0.61;0.82) without and with MS, respectively, for Top 1; 0.87 (0.79;0.95) for Top 2; and 0.90 (0.83;0.97) for Top 3. Our AI model appears to be a promising tool for triaging and diagnosing skin lesions, especially for non-specialist physicians.
SN - 1167-1122
SN - 1952-4013
ER -