Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Dec 12, 2022
Date Accepted: Feb 4, 2023
AI-based Psoriasis Severity Assessment: A Real World Study and Application
ABSTRACT
Background:
Psoriasis is one of the most frequent inflammatory skin conditions and could be treated via tele-dermatology, provided that the current lackage of reliable tools for objective severity assessments were overcome. Psoriasis Area and Severity Index (PASI) has a prominent level of subjectivity and rarely been used in the real practice, although it is the most widely accepted metric for measuring psoriasis severity currently.
Objective:
To develop an image-AI-based validated system for severity assessment with the explicit intention of facilitating long-term management of patients with psoriasis.
Methods:
A deep learning system was trained to estimate the PASI score by using 2,367 psoriasis patients with 14,096 images. 1,962 patients from January 2015 to April 2021 were used to train the model, and the other 405 patients from May 2021 to July 2021 to validate. A multi-view feature enhancement block were designed to combine vision features from different perspectives, to better simulate the visual diagnostic method in clinical practice. A classification header along with a regression header simultaneously was applied to generate PASI scores, and an extra cross teacher header after these two headers were designed to revise their output. The MAE (mean average error) is used as metric to evaluate the accuracy of the predicted PASI. Then, the proposed model was compared with 43 experienced dermatologists. Finally, the proposed model was deployed into an APP named SkinTeller on the Wechat platform.
Results:
The proposed image-AI-based PASI estimating model outperforms the average performance of 43 experienced dermatologists with a 33.2% performance gain in overall index of PASI. The model achieves the smallest MAE of 2.05 at three input images by the ablation experiment. The APP SkinTeller has been used in 1497 patients from 18 hospitals for 3,369 times of PASI scoring and its excellent performance was confirmed by a feedback survey of 43 dermatologist users.
Conclusions:
An image-AI-based psoriasis severity assessment model are proposed to automatically calculate PASI score in an efficient, objective and accurate manner. The APP SkinTeller maybe a promising alternative for dermatologists’ accurate assessment in the real world and chronic disease self-management in patients with psoriasis.
Citation
Per the author's request the PDF is not available.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.