AI-Augmented Review Identifies Key Biomarkers in Childhood Atopic Dermatitis

An artificial intelligence (AI)-assisted systematic review has synthesized evidence across genetic, immune, microbial, and metabolic biomarkers in childhood atopic dermatitis (AD), providing a systems-level framework for understanding disease pathogenesis while identifying biomarkers supported by the strongest evidence.

Childhood AD remains one of the most common inflammatory skin diseases and a major source of disease burden. Although numerous biomarker studies have been published, prior reviews have generally focused on individual molecular domains rather than integrating findings across biologic systems.

To address this gap, investigators used an AI-augmented review process in which ASReview supported title and abstract screening and ChatGPT assisted structured data extraction with human validation. Across 526 studies, the review identified 141 genomic, 95 immunomic, 57 microbiome, and 75 metabolomic biomarkers associated with childhood AD.

Among the most frequently reported biomarkers were filaggrin, IgE, CCL17, Staphylococcus, Bifidobacterium, and vitamin D. Using a structured evidence-grading framework, 8 biomarkers demonstrated the strongest evidence: IgE, CCL17, CCL27, eosinophil cationic protein, eosinophils, IL-18, IL-31, and Escherichia.

The investigators integrated findings across biologic domains to develop a conceptual model of childhood AD. According to the authors, “barrier defects, Th2 inflammation, microbial dysbiosis, and metabolic imbalance drive a self-perpetuating cycle of inflammation and barrier dysfunction.”

The review also highlights the potential value of multimodal approaches to disease management. The authors state that the findings “support the rationale for approaches that consider multiple biological nodes,” including barrier repair, immune modulation, microbiome-directed strategies, and metabolic factors. However, they emphasize that additional validation is required before these biomarkers can be incorporated into routine clinical practice.

Reference

Lee JW, Loo EXL, Chong SS, Ban KHK, Lee CG. An AI-augmented review of childhood atopic dermatitis biomarkers across genetic, immune, microbial, and metabolic domains. Mol Med. Published online July 4, 2026. doi:10.1186/s10020-026-01533-1