Artificial Intelligence in Patch Testing: Comprehensive Review of Current Applications and Future Prospects in Dermatology

TL;DR

This paper reviews how AI is being used in patch testing for skin allergies, highlighting its potential to improve accuracy and standardization, while also identifying key challenges.

Contribution

The paper provides a comprehensive review of AI applications in patch testing and outlines necessary steps for clinical implementation.

Findings

Most AI studies in patch testing used CNNs with accuracy rates between 90.1% and 99.5%.

Key limitations include small sample sizes and inconsistent image capture protocols.

Standardized protocols and diverse datasets are needed for broader AI adoption in dermatology.

Abstract

The integration of artificial intelligence (AI) into patch testing for allergic contact dermatitis (ACD) holds the potential to standardize diagnoses, reduce interobserver variability, and improve overall diagnostic accuracy. However, the challenges and limitations hindering clinical implementation have not been thoroughly explored.

This narrative review aims to examine the current applications of AI in patch testing, identify challenges, and propose future directions for their use in dermatology.

PubMed was searched in August 2024 to identify studies involving human participants undergoing patch testing with AI used in the study. Exclusion criteria were non-English and nonoriginal research. Data were synthesized to assess study design, performance, and potential for clinical application.

Out of 94 reviewed articles, 10 met the inclusion criteria. Most studies employed convolutional neural networks (CNN) for image analysis, with accuracy rates ranging from 90.1% to 99.5%. Other AI models, such as gradient boosting and random forest, were used for risk prediction and biomarker discovery. Key limitations included limited sample sizes, variability in image capture protocols, and lack of standardized reporting on skin types.

AI has significant potential to enhance diagnostic accuracy, standardize patch test interpretation, and expand access to patch testing. However, standardized imaging protocols, larger and more diverse datasets, and improved regulatory frameworks are necessary to realize the full potential of AI in patch testing.

Figures