Educational Artificial Intelligence Software to Support Assessment of Atopic Dermatitis Severity
4 affiliations
- 1Specialty Care Medical Affairs Pfizer Japan Inc. Tokyo Japan
- 2Medical Enablement & Quality, Chief Medical Office Pfizer Belgium Brussels Belgium
- 3Digital Pfizer Japan Inc. Tokyo Japan
- 4M3 Inc. Tokyo Japan
Abstract
Accurate assessment of the severity of atopic dermatitis is crucial for guiding treatment. However, the Eczema Area and Severity Index (EASI), a widely used clinical assessment tool, relies on subjective visual scoring, which can lead to inter‐rater variability. This study aimed to evaluate the performance of convolutional neural network‐based artificial intelligence software in assessing atopic dermatitis severity from uncropped, unmasked skin images acquired under uncontrolled conditions. In this prospective, multicenter observational study involving 16 Japanese institutions, 1016 patients with atopic dermatitis provided 3676 smartphone‐captured skin images. A ConvNeXt‐based artificial intelligence model was trained to predict the severity scores for four established signs of the EASI—erythema, papulation/edema, excoriation, and lichenification—and these were evaluated using receiver operating characteristic analysis against dermatologist assessments. For an EASI component score of ≥ 2, the area under the receiver operating characteristic curve ranged from 0.825 to 0.860 across signs, with sensitivities of 0.745–0.873 and specificities of 0.675–0.764. For a component severity score of 3, the area under the receiver operating characteristic curve exceeded 0.900, with sensitivity up to 1.000 and specificity up to 0.906. The area under the receiver operating characteristic curve for a severity score of ≥ 1 remained consistently > 0.700. Among the four evaluated signs, erythema demonstrated the highest accuracy, whereas papulation/edema showed the lowest. This ConvNeXt‐based artificial intelligence software demonstrated robust performance in evaluating atopic dermatitis severity using real‐world images. As an educational tool, it may support standardized training and reduce inter‐rater variability in EASI sign scoring. It is not intended for direct clinical decision‐making at this stage.
Related
- PACS-Integrated Artificial Intelligence-Based Software Tool for Rapid and Fully Automatic Bone Fracture Assessment of the Tibial Plateau
- Artificial Intelligence-Driven Dietary Assessment Software: A Structured Narrative Review of Technological Advances, Persistent Measurement Error and Barriers to Clinical Translation
- Atopic Dermatitis in the Era of Exposome and Artificial Intelligence
- Artificial Intelligence and Anatomical Variation: A Narrative Review of Detection, Classification, and Educational Applications.
- Enhancing Medical Students' Disease Detection Skills: Leveraging Artificial Intelligence Software for Diagnosing Developmental Dysplasia Using Ultrasound Imaging.
BibTeX
@article{yamanaka2026educational,
title = {{Educational Artificial Intelligence Software to Support Assessment of Atopic Dermatitis Severity}},
author = {Kenichi Yamanaka and Yağmur Pak and Yoshihiro Inda and Toshiaki Nomi and Keisuke Ogaki and Masato Hoshi and Kouki Nakamura},
journal = {The Journal of Dermatology},
year = {2026},
month = jul,
doi = {10.1111/1346-8138.70434},
url = {https://doi.org/10.1111/1346-8138.70434},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Educational Artificial Intelligence Software to Support Assessment of Atopic Dermatitis Severity
AU - Kenichi Yamanaka
AU - Yağmur Pak
AU - Yoshihiro Inda
AU - Toshiaki Nomi
AU - Keisuke Ogaki
AU - Masato Hoshi
AU - Kouki Nakamura
PY - 2026
DA - 2026/07/30
JO - The Journal of Dermatology
DO - 10.1111/1346-8138.70434
UR - https://doi.org/10.1111/1346-8138.70434
AB - Accurate assessment of the severity of atopic dermatitis is crucial for guiding treatment. However, the Eczema Area and Severity Index (EASI), a widely used clinical assessment tool, relies on subjective visual scoring, which can lead to inter‐rater variability. This study aimed to evaluate the performance of convolutional neural network‐based artificial intelligence software in assessing atopic dermatitis severity from uncropped, unmasked skin images acquired under uncontrolled conditions. In this prospective, multicenter observational study involving 16 Japanese institutions, 1016 patients with atopic dermatitis provided 3676 smartphone‐captured skin images. A ConvNeXt‐based artificial intelligence model was trained to predict the severity scores for four established signs of the EASI—erythema, papulation/edema, excoriation, and lichenification—and these were evaluated using receiver operating characteristic analysis against dermatologist assessments. For an EASI component score of ≥ 2, the area under the receiver operating characteristic curve ranged from 0.825 to 0.860 across signs, with sensitivities of 0.745–0.873 and specificities of 0.675–0.764. For a component severity score of 3, the area under the receiver operating characteristic curve exceeded 0.900, with sensitivity up to 1.000 and specificity up to 0.906. The area under the receiver operating characteristic curve for a severity score of ≥ 1 remained consistently > 0.700. Among the four evaluated signs, erythema demonstrated the highest accuracy, whereas papulation/edema showed the lowest. This ConvNeXt‐based artificial intelligence software demonstrated robust performance in evaluating atopic dermatitis severity using real‐world images. As an educational tool, it may support standardized training and reduce inter‐rater variability in EASI sign scoring. It is not intended for direct clinical decision‐making at this stage.
SN - 0385-2407
SN - 1346-8138
ER -