CoChat
Sign Up
Cited by 70Psoriasis: Treatment and PathogenesisArtificial Intelligence in Healthcare and EducationDermatology and Skin Diseases

Artificial intelligence-based psoriasis severity assessment: real-world study and application

Open access
Huang, Kai, Wu, Xian, Li, Yixin, Lv, Chengzhi, Yan, Yangtian, Wu, Zhe, Zhang, Mi, Huang, Weihong +24 more·2023·Journal of Medical Internet Research
DOI 10.2196/44932PMC PMC10131673

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Background: Psoriasis is one of the most frequent inflammatory skin conditions and could be treated via tele-dermatology, provided that the current lack of reliable tools for objective severity assessments is overcome. Psoriasis Area and Severity Index (PASI) has a prominent level of subjectivity and is rarely used in real practice, although it is the most widely accepted metric for measuring psoriasis severity currently. Objective: This study aimed to develop an image–artificial intelligence (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 14,096 images from 2367 patients with psoriasis. We used 1962 patients from January 2015 to April 2021 to train the model and the other 405 patients from May 2021 to July 2021 to validate it. A multiview feature enhancement block was 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 was simultaneously applied to generate PASI scores, and an extra cross-teacher header after these 2 headers was designed to revise their output. The mean average error (MAE) was used as the metric to evaluate the accuracy of the predicted PASI score. By making the model minimize the MAE value, the model becomes closer to the target value. 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 outperformed the average performance of 43 experienced dermatologists with a 33.2% performance gain in the overall PASI score. The model achieved the smallest MAE of 2.05 at 3 input images by the ablation experiment. In other words, for the task of psoriasis severity assessment, the severity score predicted by our model was close to the PASI score diagnosed by experienced dermatologists. The SkinTeller app has been used 3369 times for PASI scoring in 1497 patients from 18 hospitals, and its excellent performance was confirmed by a feedback survey of 43 dermatologist users. Conclusions: An image-AI–based psoriasis severity assessment model has been proposed to automatically calculate PASI scores in an efficient, objective, and accurate manner. The SkinTeller app may be a promising alternative for dermatologists’ accurate assessment in the real world and chronic disease self-management in patients with psoriasis.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2196/44932

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • AI applications in dermatology have expanded beyond diagnosis and shifted towards assessing disease severity.

    “Artificial intelligence (AI) applications in dermatology have expanded beyond diagnosis and have shifted towards assessing disease severity.”

    From Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis (2025) · cites this paper as [6]

    The Introduction says AI has been used to diagnose and evaluate skin diseases, and the paper develops an AI system to assess psoriasis severity. It does not establish a field-wide shift toward severity assessment; it says prior AI work in psoriasis focused mainly on diagnosis and that only a few severity-rating attempts had been made. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 26

  1. [1]Raho G Koleva DM Garattini L Naldi L The burden of moderate to severe psoriasis: an overview Pharmacoeconomics 2012 11 01 30 11 1005 13 10.2165/11591580-000000000-00000 22994598 22994598 · DOI
  2. [2]Armstrong AW Read C Pathophysiology, clinical presentation, and treatment of psoriasis: a review JAMA 2020 05 19 323 19 1945 1960 10.1001/jama.2020.4006 32427307 2766169 32427307 · DOI
  3. [3]Feldman SR Burudpakdee C Gala S Nanavaty M Mallya UG The economic burden of psoriasis: a systematic literature review Expert Rev Pharmacoecon Outcomes Res 2014 10 23 14 5 685 705 10.1586/14737167.2014.933671 25052261 25052261 · DOI
  4. [4]Parisi R Iskandar IYK Kontopantelis E Augustin M Griffiths CEM Ashcroft DM Global Psoriasis Atlas National, regional, and worldwide epidemiology of psoriasis: systematic analysis and modelling study BMJ 2020 05 28 369 m1590 10.1136/bmj.m1590 32467098 32467098 PMC7254147 · DOI
  5. [5]Boehncke W Menter A Burden of disease: psoriasis and psoriatic arthritis Am J Clin Dermatol 2013 10 15 14 5 377 88 10.1007/s40257-013-0032-x 23771648 23771648 · DOI
  6. [6]Griffiths CEM Armstrong AW Gudjonsson JE Barker JNWN Psoriasis Lancet 2021 04 03 397 10281 1301 1315 10.1016/S0140-6736(20)32549-6 33812489 S0140-6736(20)32549-6 33812489 · DOI
  7. [7]Menter A Gottlieb A Feldman SR Van Voorhees AS Leonardi CL Gordon KB Lebwohl M Koo JY Elmets CA Korman NJ Beutner KR Bhushan R Guidelines of care for the management of psoriasis and psoriatic arthritis: section 1. overview of psoriasis and guidelines of care for the treatment of psoriasis with biologics J Am Acad Dermatol 2008 05 58 5 826 50 10.1016/j.jaad.2008.02.039 18423260 S0190-9622(08)00273-9 18423260 · DOI
  8. [8]Cabrera S Chinniah N Lock N Cains GD Woods J Inter-observer reliability of the PASI in a clinical setting Australas J Dermatol 2015 05 05 56 2 100 2 10.1111/ajd.12280 25753553 25753553 · DOI
  9. [9]Fink C Alt C Uhlmann L Klose C Enk A Haenssle H Intra- and interobserver variability of image-based PASI assessments in 120 patients suffering from plaque-type psoriasis J Eur Acad Dermatol Venereol 2018 08 27 32 8 1314 1319 10.1111/jdv.14960 29569769 29569769 · DOI
  10. [10]Khan A Sohail A Zahoora U Qureshi AS A survey of the recent architectures of deep convolutional neural networks Artif Intell Rev 2020 04 21 53 8 5455 5516 10.1007/s10462-020-09825-6 · DOI · Paper page
  11. [11]Hossen MN Panneerselvam V Koundal D Ahmed K Bui FM Ibrahim SM Federated machine learning for detection of skin diseases and enhancement of Internet of Medical Things (IoMT) security IEEE J Biomed Health Inform 2022 02 08 27 2 835 841 10.1109/JBHI.2022.3149288 35133971 35133971 · DOI
  12. [12]Yang Y Wang J Xie F Liu J Shu C Wang Y Zheng Y Zhang H A convolutional neural network trained with dermoscopic images of psoriasis performed on par with 230 dermatologists Comput Biol Med 2021 12 139 104924 10.1016/j.compbiomed.2021.104924 34688173 S0010-4825(21)00718-6 34688173 · DOI
  13. [13]Huang K Jiang Z Li Y Wu Z Wu X Zhu W Chen M Zhang Y Zuo K Li Y Yu N Liu S Huang X Su J Yin M Qian B Wang X Chen X Zhao S The classification of six common skin diseases based on Xiangya-Derm: development of a Chinese database for artificial intelligence J Med Internet Res 2021 09 21 23 9 e26025 10.2196/26025 34546174 v23i9e26025 34546174 PMC8493463 · DOI
  14. [15]Schaap M Cardozo N Patel A de Jong E M G J van Ginneken B Seyger M Image-based automated Psoriasis Area Severity Index scoring by convolutional neural networks J Eur Acad Dermatol Venereol 2022 01 18 36 1 68 75 10.1111/jdv.17711 34653265 34653265 PMC9298301 · DOI
  15. [16]Fink C Alt C Uhlmann L Klose C Enk A Haenssle H Precision and reproducibility of automated computer-guided Psoriasis Area and Severity Index measurements in comparison with trained physicians Br J Dermatol 2019 02 14 180 2 390 396 10.1111/bjd.17200 30218575 30218575 · DOI
  16. [17]Iyatomi H Oka H Hagiwara M Miyake A Kimoto M Ogawa K Tanaka M Computerized quantification of psoriasis lesions with colour calibration: preliminary results Clin Exp Dermatol 2009 10 34 7 830 3 10.1111/j.1365-2230.2008.03169.x 19438532 CED3169 19438532 · DOI
  17. [18]Kislal EE Halasz CL Software for quantifying psoriasis and vitiligo from digital clinical photographs J Dermatolog Treat 2013 04 31 24 2 107 11 10.3109/09546634.2011.596184 21801117 21801117 · DOI
  18. [19]Gertreuer P Automatic color enhancement (ACE) and its fast implementation Image Processing On Line 2012 2 266 277 10.5201/ipol.2012.g-ace · DOI
  19. [20]Meienberger N Anzengruber F Amruthalingam L Christen R Koller T Maul J Pouly M Djamei V Navarini A Observer-independent assessment of psoriasis-affected area using machine learning J Eur Acad Dermatol Venereol 2020 06 23 34 6 1362 1368 10.5167/uzh-179575 31594034 31594034 · DOI
  20. [22]Guo K Shen C Hu B Hu M Kui X RSNet: relation separation network for few-shot similar class recognition IEEE Trans Multimedia 2022 4 19 1 1 10.1109/tmm.2022.3168146 · DOI
  21. [23]Zhao S Xie B Li Y Zhao X Kuang Y Su J He X Wu X Fan W Huang K Su J Peng Y Navarini A Huang W Chen X Smart identification of psoriasis by images using convolutional neural networks: a case study in China J Eur Acad Dermatol Venereol 2020 03 17 34 3 518 524 10.1111/jdv.15965 31541556 31541556 · DOI
  22. [24]Ahmad Fadzil MH Ihtatho D Mohd Affandi A Hussein SH Objective assessment of psoriasis erythema for PASI scoring J Med Eng Technol 2009 09 15 33 7 516 24 10.1080/07434610902744074 19639508 913495095 19639508 · DOI
  23. [25]Lu J Manton JH Kazmierczak E Sinclair R Erythema detection in digital skin images 2010 12 3 2010 IEEE International Conference on Image Processing September 26-29, 2010 Hong Kong, China 2545 2548 10.1109/icip.2010.5653524 · DOI
  24. [26]Delgardo D Ersbøll B Carstensen JM An image based system to automatically and objectively score the degree of redness and scaling in psoriasis lesions 2004 13th Danish Conference on Image Analysis and Pattern Recognition August 19-20, 2004 Copenhagen, Denmark 130 137
  25. [27]Pal A Chaturvedi A Garain U Chandra A Chatterjee R Severity grading of psoriatic plaques using deep CNN based multi-task learning 2017 4 24 2016 23rd International Conference on Pattern Recognition (ICPR) December 4-8, 2016 Cancun, Mexico 1478 1483 10.1109/icpr.2016.7899846 · DOI
  26. [28]Pal A Chaturvedi A Garain U Chandra A Chatterjee R Senapati S Severity assessment of psoriatic plaques using deep CNN based ordinal classification 2018 10 2 CARE 2018, CLIP 2018, OR 2.0 2018, ISIC 2018: OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis September 16 and 20, 2018 Granada, Spain 252 259 10.1007/978-3-030-01201-4_27 · DOI

Cited by

Sorted by citations

Authors
Huang, K., Wu, X., Li, Y., Lv, C., Yan, Y., Wu, Z., Zhang, M., Huang, W., Jiang, Z., Hu, K., Li, M., Su, J., Zhu, W., Li, F., Chen, M., Chen, J., Li, Y., Zeng, M., Zhu, J., Cao, D., Huang, X., Huang, L., Hu, X., Chen, Z., Kang, J., Yuan, L., Huang, C., Guo, R., Navarini, A., Kuang, Y., Chen, X., & Zhao, S.
Affiliations
  • Central South University (CN)
  • Tencent (China) (CN)
  • Dalian Dermatosis Hospital (CN)
  • Xiangya Hospital Central South University (CN)
  • The Central Hospital of Shaoyang (CN)
  • The First People's Hospital of Changde (CN)
  • Hunan Normal University (CN)
  • China Mobile (China) (CN)
  • University Hospital of Basel (CH)
Corresponding author
Zhao, Shuang
ORCID
Venue
Journal of Medical Internet Research
Publisher
JMIR Publications Inc.
Published
2023-03-16
Volume
25
Pages
e44932
ISSN
1438-8871 (ISSN-L)
DOI
10.2196/44932
PMC
PMC10131673
OpenAlex
W4327575282
Cited by
70
References
1
Citations by year
2026: 18 · 2025: 28 · 2024: 17 · 2023: 7
FWCI
7.67
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Journal of Medical Internet Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Central South University
  • Ministry of Industry and Information Technology of the People's Republic of China (TC210804V)
  • Hunan Provincial Innovation Foundation for Postgraduate
  • Fundamental Research Funds for the Central Universities
Topics
  • Life Sciences › Immunology and Microbiology › Immunology › Psoriasis: Treatment and Pathogenesis
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Dermatology › Dermatology and Skin Diseases
Keywords
psoriasis, psoriasis severity assessment, teledermatology, dermatological image analysis, deep learning, dermatologist comparison, mobile health apps, WeChat, long-term disease management, user feedback survey
MeSH terms
Artificial Intelligence, Chronic Disease, Humans, Psoriasis, Surveys and Questionnaires, Severity of Illness Index

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review