文献速递银屑病与炎症性皮肤病湿疹皮炎与荨麻疹

人工智能模型评估炎症性皮肤病严重程度的系统综述与荟萃分析

Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis.
PubMed 文献 · Br J Dermatol · 2025-01-01

该研究系统检索四个数据库并纳入45项研究进行系统综述,其中19项用于荟萃分析,评估基于图像的AI模型对皮肤病严重程度的评估性能。合并敏感度为80.5%(95%CI 76.2-84.2),特异度为96.2%(95%CI 94.9-97.2);合并敏感度因疾病类型和评分系统而异。结论认为当前AI模型在严重程度评估方面表现较高,但需提高数据报告透明度并开展高质量前瞻性研究。

要点

  • AI模型评估皮肤病严重程度的合并敏感度为80.5%,特异度为96.2%。
  • 合并敏感度因疾病类型和评分系统不同而存在显著差异。
  • 需提高数据报告透明度并开展高质量前瞻性研究以生成可靠证据。

核心结论

  • 当前AI模型在皮肤病严重程度评估方面表现出较高能力,但需改进数据报告透明度并开展高质量前瞻性研究。

研究设计与样本

  • 纳入评估深度学习AI模型对皮肤病严重程度性能的研究,排除使用未经验证严重程度指数、缺乏临床图像以及评估伤口、溃疡或烧伤的研究。
  • 初检发现7737条记录,全文审查192篇后纳入45项研究进行系统综述,其中19项纳入荟萃分析;研究注册于PROSPERO(CRD42023487228)。

主要发现

  • AI模型的合并敏感度为80.5%(95%CI 76.2-84.2),合并特异度为96.2%(95%CI 94.9-97.2)。
  • 合并敏感度因疾病类型而异:特应性皮炎为91.8%,痤疮为80.7%(P=0.005);痤疮为80.4%,银屑病为71.1%(P=0.044)。
  • 合并敏感度因评分系统而异:特应性皮炎湿疹面积和严重程度指数(EASI)为97.3%,研究者总体评估(IGA)为78.9%(P<0.001);痤疮Hayashi分级为89.7%,IGA为69.8%(P<0.001)。

关键数值与推荐

  • AI模型合并敏感度80.5%(95%CI 76.2-84.2),合并特异度96.2%(95%CI 94.9-97.2)。
  • 特应性皮炎合并敏感度91.8%,痤疮80.7%(P=0.005);痤疮80.4%,银屑病71.1%(P=0.044)。
  • 特应性皮炎EASI合并敏感度97.3%,IGA 78.9%(P<0.001);痤疮Hayashi分级89.7%,IGA 69.8%(P<0.001)。

临床怎么用

  • AI模型可作为医生评估皮肤病严重程度的辅助工具,但需注意其性能因疾病类型和评分系统而异。

局限性

  • 需要改进数据报告的透明度,并开展使用客观参考标准的高质量前瞻性临床研究以生成可靠证据。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

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. Artificial intelligence (AI) can have several uses in dermatology. It can be used in the diagnosis of skin diseases and to assess disease severity. In this study, we conducted a systematic review and meta-analysis looking at how well AI can judge the severity of skin diseases. To do this, we reviewed research studies using AI models for different skin conditions published between 2017 and 2023. We found that AI can be highly accurate in assessing skin disease severity. On average, AI correctly identified the severity of skin diseases 81% of the time. In some cases, it was even more precise (96%). However, the accuracy varied depending on the type of skin disease and the scoring system used. Our findings show that AI could be a valuable tool for doctors in assessing skin conditions. However, this study also highlights the need for better data reporting and further high-quality, real-world studies to ensure more reliable results.

来源:Br J Dermatol,查看原文。版权归原作者所有。

引用

  1. Cai ZR, Kim J, Rezaei SJ, et al. Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis. Br J Dermatol. 2025. PMID: 40570030. doi:10.1093/bjd/ljaf250

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。