Diagnosing contact dermatitis using machine learning: A review

IF 4.8 1区医学 Q2 ALLERGY Contact Dermatitis Pub Date : 2024-06-03 DOI:10.1111/cod.14595

Eric McMullen, Rajan Grewal, Kyle Storm, Mahan Maazi, Abu Bakar Butt, Raghav Gupta, Howard Maibach

{"title":"Diagnosing contact dermatitis using machine learning: A review","authors":"Eric McMullen, Rajan Grewal, Kyle Storm, Mahan Maazi, Abu Bakar Butt, Raghav Gupta, Howard Maibach","doi":"10.1111/cod.14595","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Machine learning (ML) offers an opportunity in contact dermatitis (CD) research, where with full clinical picture, may support diagnosis and patch test accuracy.</p>\n </section>\n \n <section>\n \n <h3> Objective</h3>\n \n <p>This review aims to summarise the existing literature on how ML can be applied to CD in its entirety.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Embase, Medline, IEEE Xplore, and ACM Digital Library were searched from inception to February 7, 2024, for primary literature reporting on ML models in CD.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>7834 articles were identified in the search, with 110 moving to full-text review, and six articles included. Two used ML to identify key biomarkers to help distinguish between allergic contact dermatitis (ACD) and irritant contact dermatitis (ICD), three used image data to distinguish between ACD and ICD, and one used clinical and demographical data to predict the risk of positive patch tests. All studies used supervision in their ML model training with a total of 49 704 patients across all data sets. There was sparse reporting of the accuracy of these models.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>Although the available research is still limited, there is evidence to suggest that ML has potential to support diagnostic outcomes in a clinical setting. Further research on the use of ML in clinical practice is recommended.</p>\n </section>\n </div>","PeriodicalId":10527,"journal":{"name":"Contact Dermatitis","volume":null,"pages":null},"PeriodicalIF":4.8000,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cod.14595","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Contact Dermatitis","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/cod.14595","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ALLERGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Machine learning (ML) offers an opportunity in contact dermatitis (CD) research, where with full clinical picture, may support diagnosis and patch test accuracy.

Objective

This review aims to summarise the existing literature on how ML can be applied to CD in its entirety.

Methods

Embase, Medline, IEEE Xplore, and ACM Digital Library were searched from inception to February 7, 2024, for primary literature reporting on ML models in CD.

Results

7834 articles were identified in the search, with 110 moving to full-text review, and six articles included. Two used ML to identify key biomarkers to help distinguish between allergic contact dermatitis (ACD) and irritant contact dermatitis (ICD), three used image data to distinguish between ACD and ICD, and one used clinical and demographical data to predict the risk of positive patch tests. All studies used supervision in their ML model training with a total of 49 704 patients across all data sets. There was sparse reporting of the accuracy of these models.

Conclusions

Although the available research is still limited, there is evidence to suggest that ML has potential to support diagnostic outcomes in a clinical setting. Further research on the use of ML in clinical practice is recommended.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用机器学习诊断接触性皮炎：综述。

背景：机器学习（ML）为接触性皮炎（CD）研究提供了机会：机器学习（ML）为接触性皮炎（CD）研究提供了一个机会，通过完整的临床图片，可以支持诊断和斑贴试验的准确性：本综述旨在总结有关如何将 ML 全面应用于 CD 的现有文献：方法：检索了 Embase、Medline、IEEE Xplore 和 ACM 数字图书馆从开始到 2024 年 2 月 7 日期间有关 ML 模型在 CD 中应用的主要文献：结果：共检索到 7834 篇文章，其中 110 篇进入全文审阅，6 篇被收录。其中两篇文章使用ML识别关键生物标志物，帮助区分过敏性接触性皮炎（ACD）和刺激性接触性皮炎（ICD）；三篇文章使用图像数据区分ACD和ICD；一篇文章使用临床和人口统计学数据预测斑贴试验阳性的风险。所有研究都使用了监督方法对所有数据集的 49 704 名患者进行 ML 模型训练。关于这些模型准确性的报告很少：尽管现有研究还很有限，但有证据表明，ML 有潜力为临床诊断结果提供支持。建议进一步研究 ML 在临床实践中的应用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Contact Dermatitis 医学-过敏

CiteScore

4.60

自引率

30.90%

发文量

227

审稿时长

4-8 weeks

期刊介绍： Contact Dermatitis is designed primarily as a journal for clinicians who are interested in various aspects of environmental dermatitis. This includes both allergic and irritant (toxic) types of contact dermatitis, occupational (industrial) dermatitis and consumers" dermatitis from such products as cosmetics and toiletries. The journal aims at promoting and maintaining communication among dermatologists, industrial physicians, allergists and clinical immunologists, as well as chemists and research workers involved in industry and the production of consumer goods. Papers are invited on clinical observations, diagnosis and methods of investigation of patients, therapeutic measures, organisation and legislation relating to the control of occupational and consumers".