The DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index; 15 of the 22 sources its claims cite were checked for support.
Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis
Open accessAbstract
Background: Artificial intelligence (AI) applications in dermatology have expanded beyond diagnosis and have shifted towards assessing disease severity. Objectives: To qualitatively and quantitatively evaluate the performance of image-based AI models in severity assessment for various skin diseases. Methods: In this systematic review and meta-analysis, we collected studies using four electronic databases, including PubMed, Embase, Institute of Electrical and Electronics Engineers Xplore and Web of Science, published from 1 January 2017 to 6 April 2023, and updated the search in November 2023. Studies assessing the performance of deep learning AI models on the severity of skin diseases were included. We excluded studies that utilized a nonvalidated severity index, lacked clinical images, and assessed wounds, ulcers or burns. Two independent reviewers extracted prespecified study characteristics for the summary table. For the meta-analysis, contingency tables were extracted, when possible, and reconstructed for each severity measure. Accuracy was calculated using a bivariate model in Metandi package, and meta-regression was performed by disease type and scoring system. This study was registered with PROSPERO (CRD42023487228). Results: Our initial search identified 7737 records. After duplicate removal and abstract screening, we reviewed the full text of 192 articles and included 45 studies for systematic review and 19 for meta-analysis. The pooled sensitivity and specificity of AI models were 80.5% [95% confidence interval (CI) 76.2–84.2] and 96.2% (95% CI 94.9–97.2), respectively. Moreover, pooled sensitivity differed by disease (atopic dermatitis 91.8% vs. acne 80.7%, P = 0.005; acne 80.4% vs. psoriasis 71.1%, P = 0.044) and scoring system [Eczema Area and Severity Index 97.3% vs. Investigator’s Global Assessment (IGA) for atopic dermatitis 78.9%, P < 0.001; Hayashi Grading 89.7% vs. IGA for acne 69.8%, P < 0.001]. Conclusions: Our findings show that current AI models exhibit a high level of capacity in disease severity assessment. Nevertheless, efforts are urgently needed to improve transparency in data reporting and conduct high-quality prospective studies using objective reference standards in clinical settings to generate reliable evidence.
Overview
CoChat Summary
TL;DR
This systematic review and meta-analysis found that image-based AI models assess inflammatory skin disease severity with high pooled specificity and moderate-to-high sensitivity, though performance varied by disease and scoring system. The authors emphasize limited transparency, retrospective designs, and poor skin tone reporting as barriers to reliable clinical use.
Key findings
- From 45 included studies and 19 in meta-analysis, pooled AI sensitivity was 80.5% (95% CI 76.2–84.2) and pooled specificity was 96.2% (95% CI 94.9–97.2); pooled reliability was 78.0% (95% CI 72.2–83.8).
- Sensitivity differed by disease: atopic dermatitis 91.8% vs. acne 80.7% (P = 0.005), and acne 80.4% vs. psoriasis 71.1% (P = 0.044). Specificity was highest in atopic dermatitis (98.1% vs. acne 94.3%, P = 0.014).
- Scoring system mattered: for atopic dermatitis, EASI sensitivity was 97.3% vs. IGA 78.9% (P < 0.001); for acne, Hayashi Grading/New Acne Severity sensitivity was 89.7% vs. IGA 69.8% (P < 0.001).
- Most studies were from Asia (64%, 29/45) and Europe (29%, 13/45); psoriasis (31%, 14/45), acne (27%, 12/45), and atopic dermatitis (9%, 4/45) were most studied.
Methods
- Systematic review and meta-analysis registered with PROSPERO (CRD42023487228), searching PubMed, Embase, IEEE Xplore, and Web of Science from 1 January 2017 to 6 April 2023, updated November 2023; 7,737 records initially identified, 45 studies included in systematic review and 19 in meta-analysis.
- Included studies assessed deep learning/CNN AI models for severity of skin, hair, or nail diseases using clinical images and validated severity indices; excluded nonvalidated indices, segmentation-only studies, wounds, ulcers, burns, tumours, and photoageing.
- Pooled sensitivity/specificity used a bivariate model in Stata 18 Metandi; meta-regression by disease type and scoring system used Meqrlogit; risk of bias assessed with QUADAS-2, with Deeks’ funnel plot asymmetry test for publication bias.
Limitations
- The paper states that analysis was limited to studies providing contingency tables or ICCs, multiple contingency tables were treated independently, acne scoring systems were combined for subgroup analysis, and high heterogeneity limits generalizability; a small-study effect was noted for reliability.
- The paper states that more than 75% of studies (78%, 35/45) did not report skin tone data, preventing assessment across diverse populations; most studies used private datasets, few reported demographic or skin tone metadata, and only one used a prospective design.
- Evident from the text: one-third of studies had high risk of bias (n = 14), QUADAS-2 interrater agreement was low (κ = 0.27), and most studies were retrospective or proof-of-concept rather than clinical prospective validations.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures



Verification
Claims the paper makes
10 Valid · 0 Not valid · 6 Not checked · 76 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Previous reviews of image-based AI algorithms have consistently raised concerns about the lack of transparency in metadata reporting.69”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Discussion
What the sources say
- Partly supportedcites [69] Collins, 2021, Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence, BMJ Open sourceExperimental — accuracy not yet measured
The Background reports that a few reviews found poor reporting in machine-learning prediction-model studies. It does not say those reviews consistently concerned image-based algorithms or identify metadata reporting as the problem; the Methods/design section describes further reviews as ongoing. (LLM, conf=0.84)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Without better skin tone representation, AI severity assessment tools risk worsening health disparities, especially for darker skin tones.71”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Discussion
What the sources say
- Partly supportedcites [71] Daneshjou, 2022, Disparities in dermatology AI performance on a diverse, curated clinical image set, Sci Adv sourceExperimental — accuracy not yet measured
The Discussion (page not provided) warns that dermatology AI datasets must include dark skin tones to alleviate disparities rather than exacerbate them. The Results document worse malignancy-detection performance on darker skin tones, but the paper evaluates diagnostic tools, not AI severity assessment tools specifically. (LLM, conf=0.86)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 3 assumptions not shown here.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Notably, a meta-analysis evaluating the performance of image-based AI models for skin disease severity assessment has not been reported.15,16”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Abstract > Conclusions
What the sources say
- Partly supportedcites [15] Yu, 2020, Machine learning applications in the evaluation and management of psoriasis: a systematic review, J Psoriasis Psoriatic Arthritis sourceExperimental — accuracy not yet measured
The Results (page unavailable) say this review qualitatively synthesized 33 studies, including 12 on image-based lesion severity and area scoring; the Methods likewise describe a qualitative synthesis. That supports the narrower point that this review did not perform a performance meta-analysis, but the paper does not establish the broader claim that no such meta-analysis had been reported elsewhere. (LLM, conf=0.78)
- Could not verifycites [16] Yang, 2021, Use of technology for the objective evaluation of scratching behavior: a systematic review, JAAD Int sourceExperimental — accuracy not yet measured
The Results section reviews technologies for detecting scratching, and the Discussion addresses performance of scratch-monitoring algorithms. Neither states whether a meta-analysis of image-based AI models for skin disease severity assessment has been reported; searches for that topic found no such passage in our copy. Page numbers were not available. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Prior systematic reviews9–11 and meta-analyses12,13 have concentrated on the detection of skin cancer using image-based AI models”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Abstract > Conclusions
What the sources say
- Not checked — no full text of the sourcecites [9] Jones, 2022, Artificial intelligence and machine learning algorithms for early detection of skin cancer in community and primary care settings: a systematic review, Lancet Digit Health source
- Partly supportedcites [10] Jeong, 2022, Deep learning in dermatology: a systematic review of current approaches, outcomes, and limitations, JID Innov sourceExperimental — accuracy not yet measured
The Introduction describes this as a review of AI applications to dermatological images, and the Results include numerous image-based melanoma and skin-cancer classification studies. But the Abstract and Results also cover other skin conditions, datasets, and clinical applications; the paper is broader than skin-cancer detection alone. No page numbers are available in our copy. (LLM, conf=0.82)
- Partly supportedcites [11] Wen, 2022, Characteristics of publicly available skin cancer image datasets: a systematic review, Lancet Digit Health sourceExperimental — accuracy not yet measured
Our copy does show that prior syntheses of image-based AI have addressed diagnostic performance: the Review section (p. ~6) refers to 'two recent systematic reviews which found that only 18-36% of studies validated their algorithms using externally sourced images', and the reference list credits Liu et al. 2019 (ref 3), Aggarwal et al. 2021 (ref 65, 'Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis'), the Cochrane CAD review (ref 66) and Dick et al. 2019 meta-analysis of melanoma CAD (ref 31). However, the copy never asserts that prior systematic reviews and meta-analyses 'concentrated on the detection of skin cancer': the syntheses it names are largely about deep learning in medical imaging broadly, and the paper's own explicit statement about the prior literature is the opposite emphasis for itself — the Introduction says skin image datasets 'have not previously been systematically characterised' and the Review declares 'this is the first systematic review of publicly available skin lesion images'. So the source is a prior systematic review in skin cancer AI, but one focused on dataset characteristics rather than on detection, and the 'concentrated on detection of skin cancer' framing is not what our copy states. (LLM, conf=0.68)
- Supportedcites [12] Dick, 2019, Accuracy of computer-aided diagnosis of melanoma: a meta-analysis, JAMA Dermatol source
Dick et al. (2019) is itself a systematic review/meta-analysis of computer-aided (image-based, AI) diagnosis of melanoma: the Abstract states that 'Most systems fall into the category of imagebased, automated diagnostic systems and use either clinical or dermoscopic images' and that the aim was to 'critically review the current literature on CAD for melanoma' and pool diagnostic accuracy. The General Study Characteristics section confirms the pooled literature is dominated by image-based methods (computer vision n=58, deep learning n=55 of 132 qualitatively included studies), and the Search Strategy restricts inclusion to screening-usable systems for cutaneous melanoma, excluding excised-lesion and invasive-technique methods. So the citing sentence's characterisation of this work as a prior meta-analysis concentrated on image-based AI detection of skin cancer (specifically melanoma) holds; the only narrower detail is that the source's target condition is melanoma rather than skin cancer in general, plus a small hardware-based minority (n=19). (LLM, conf=0.82)
- Supportedcites [13] Krakowski, 2024, Human-AI interaction in skin cancer diagnosis: a systematic review and meta-analysis, NPJ Digit Med source
The Abstract identifies this work as a systematic review and meta-analysis of AI-assisted skin cancer diagnosis. The Methods (Search strategy and selection criteria) say it included studies of clinicians detecting skin cancer with and without deep-learning AI assistance, using lesion images or in-person visits. It therefore serves as an example of the kind of prior review cited, although its specific focus is clinician–AI interaction. (LLM, conf=0.86)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Artificial intelligence (AI) applications in dermatology have expanded beyond diagnosis and have shifted towards assessing disease severity.”
- Also stated in: § Conclusions · plain
“Recently, AI applications within dermatology have expanded to grading the severity of inflammatory diseases such as psoriasis and atopic dermatitis.6”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Abstract > Background
What the sources say
- Partly supportedcites [6] Huang, 2023, Artificial intelligence-based psoriasis severity assessment: real-world study and application, J Med Internet Res sourceExperimental — accuracy not yet measured
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)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Conclusions · plain
42 more claims · 1 with their cited sources checked
Create a free account to see all 92 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 31
- Probably not a substantial claim. 22
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Abstract > Results
“Our initial search identified 7737 records.”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Results
“Initially, 7741 records were retrieved”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Abstract > Results
“we reviewed the full text of 192 articles”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Results
“reviewed 191 full texts”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Results
“12 studies with 120 contingency tables”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Results
“26, 28, 30, 36, 39, 53, 56, 61–63”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Results
“Atopic dermatitisa | EASI 0/IGA 0 (N = 8)”
§ Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis > Results
“atopic dermatitis (9%, 4 of 45)”
Citations
Cites
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · cited 1×
“4,5 Recently, AI applications within dermatology have expanded to grading the severity of inflammatory diseases such as psoriasis and atopic dermatitis.”
Self-citationReitsma, J. B., Glas, A. S., Rutjes, A. W. S., Scholten, R. J. P. M., Bossuyt, P. M., & Zwinderman, A. H. (2005) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2005.02.022 · Cited by 3,369 · cited 1×
“17,18 We plotted summary receiver operating characteristic (SROC) curves to visualize sensitivity and specificity with 95% confidence and prediction regions.”
Deeks, J. J., Macaskill, P., & Irwig, L. (2005) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2005.01.016 · Cited by 2,910
Meta-DiSc: a software for meta-analysis of test accuracy data
Zamora, J., Abraira, V., Muriel, A., Khan, K., & Coomarasamy, A. (2006) · BMC Medical Research Methodology · doi:10.1186/1471-2288-6-31 · Cited by 1,883
Liu, X., Faes, L., Kale, A. U., Wagner, S. K., Fu, D. J., Bruynseels, A., Mahendiran, T., Moraes, G., Shamdas, M., Kern, C., et al. (2019) · The Lancet Digital Health · doi:10.1016/s2589-7500(19)30123-2 · Cited by 1,883 · cited 1×
“67 This underscores the strong performance of AI, not just in identifying diseases, but also in evaluating their severity.”
The eczema area and severity index (EASI): assessment of reliability in atopic dermatitis
Hanifin, J. M., Thurston, M., Omoto, M., Cherill, R., Tofte, S. J., Graeber, M., & Evaluator Group, T. E. (2001) · Experimental Dermatology · doi:10.1034/j.1600-0625.2001.100102.x · Cited by 1,200
A deep learning system for differential diagnosis of skin diseases
Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0842-3 · Cited by 853 · cited 1×
“4,5 Recently, AI applications within dermatology have expanded to grading the severity of inflammatory diseases such as psoriasis and atopic dermatitis.”
Collins, G. S., Dhiman, P., Andaur Navarro, C. L., Ma, J., Hooft, L., Reitsma, J. B., Logullo, P., Beam, A. L., Peng, L., Van Calster, B., et al. (2021) · BMJ Open · doi:10.1136/bmjopen-2020-048008 · Cited by 852 · cited 2×
“69,70 Additionally, few studies used prospective designs.”
Disparities in dermatology AI performance on a diverse, curated clinical image set
Daneshjou, R., Vodrahalli, K., Novoa, R. A., Jenkins, M., Liang, W., Rotemberg, V., Ko, J., Swetter, S. M., Bailey, E. E., Gevaert, O., et al. (2022) · Science Advances · doi:10.1126/sciadv.abq6147 · Cited by 544 · cited 1×
“71 For example, erythema, a common marker of inflammation, is frequently underestimated and may appear more violaceous and grey in individuals with darker skin tone.”
Self-citationmetandi: Meta-analysis of diagnostic accuracy using hierarchical logistic regression
Harbord, R. M., & Whiting, P. (2009) · The Stata Journal: Promoting communications on statistics and Stata · doi:10.1177/1536867x0900900203 · Cited by 453 · cited 1×
“17,18 We plotted summary receiver operating characteristic (SROC) curves to visualize sensitivity and specificity with 95% confidence and prediction regions.”
Cited by
Dowie, T. (2025) · Cureus · doi:10.7759/cureus.94909 · Cited by 11
“Many studies lack skin tone data and therefore cannot accurately assess the efficacy of AI on varying skin tones [5].”
Szondy, I., Martyin, K., Mohos, G., Kiss, T., Szabo, K., Boostani, M., Goldust, M., Grzybowski, A. E., Bánvölgyi, A., & Kiss, N. (2026) · La Presse Médicale · doi:10.1016/j.lpm.2026.104376 · Cited by 2
Colorism as a Fundamental Cause of Inequalities in Health
Monk, E. P., & Craig, H. (2026) · Annual Review of Sociology · doi:10.1146/annurev-soc-091025-055346 · Cited by 1
Should Dermatologists Recommend Direct‐to‐Consumer App‐Based Remote Diagnostics? An Ethical Analysis
Mathes, S., Seurig, S., Willem, T., Dechant, M., Traidl, S., Kang, M., Pinto, P. M., Binder, A., Biedermann, T., & Darsow, U. (2026) · JEADV Clinical Practice · doi:10.1002/jvc2.70287
Jaing, J., & Kadam, S. J. (2026) · Trends in Pediatrics · doi:10.59213/tp.2026.384
Metadata
- Authors
- Cai, Z. R., Kim, J., Rezaei, S. J., Chen, M. L., Touma, F., Zhu, C., Onyeka, S., Fonjungo, F., Omiye, J. A., Krakowski, I., Nwandu, L., Biossonnette, R., Ko, J. M., & Linos, E.
- Affiliations
- Stanford Medicine (US)
- McGill University (CA)
- Meharry Medical College (US)
- Karolinska Institutet (SE)
- University of Illinois Urbana-Champaign (US)
- Innovaderm (Canada) (CA)
- Corresponding author
- Kim, Jiyeong
- ORCID
- Venue
- British Journal of Dermatology
- Publisher
- Oxford University Press (OUP)
- Published
- 2025-06-26
- Volume
- 193
- Issue
- 5
- Pages
- 847-855
- ISSN
- 0007-0963 (ISSN-L)
- 1365-2133
- PMC
- PMC12532143
- OpenAlex
- W4411687990
- Semantic Scholar
- 35cf9ec9d5e761a834a28a30058e1742233581fc
- Cited by
- 8
- References
- 65
- Citations by year
- 2026: 7 · 2025: 1
- FWCI
- 0.47
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- British Journal of Dermatology (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (K01MH137386)
- Midcareer Investigator Award in Patient-Oriented Research (K24AR075060)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Dermatology › Dermatology and Skin Diseases
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Keywords
- artificial intelligence, disease severity assessment, inflammatory skin diseases, deep learning, atopic dermatitis, acne, psoriasis, Eczema Area and Severity Index, Investigator's Global Assessment, diagnostic accuracy, sensitivity and specificity, dermatology, model transparency, reporting quality, generalizability, external validation, clinical scoring systems
- MeSH terms
- Deep Learning, Acne Vulgaris, Artificial Intelligence, Dermatology, Humans, 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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis. https://app.cochat.ai/papers/10.1093/bjd/ljaf250
- The paper
- Cai, Z. R., Kim, J., Rezaei, S. J., Chen, M. L., Touma, F., Zhu, C., Onyeka, S., Fonjungo, F., Omiye, J. A., Krakowski, I., Nwandu, L., Biossonnette, R., Ko, J. M., & Linos, E. (2025). Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis. British Journal of Dermatology. https://doi.org/10.1093/bjd/ljaf250
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.