Artificial intelligence diagnostic accuracy and clinical utility in allergic rhinitis management: Systematic review

Abstract

Allergic rhinitis (AR) is one of the most common outpatient conditions, diagnosed through operator-dependent and resource-intensive methodologies. This systematic review assessed the use and efficacy of diagnostic strategies using artificial intelligence (AI). This review aims to explore how AI can enhance diagnostic accuracy, personalize treatment, and support clinical decisions in AR care. This review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and was registered in PROSPERO. PubMed, Cochrane Central, Embase, and Google Scholar were searched for studies published between 2002 and 2025. Out of 1109 identified studies, eight studies met the inclusion criteria. Eight studies involving 311,354 patients fulfilled the inclusion criteria, mainly from China and South Korea. Supervised machine learning was predominant, followed by Random Forest and eXtreme Gradient Boosting algorithms. Overall, AI models demonstrated excellent diagnostic accuracy (area under the curve up to 0.93, sensitivity 91.5%, specificity 99.95%), which demonstrated a promising utility in diagnosis, risk prediction, and medication adherence. A key finding from this review is that AI models can serve as complementary tools beside gold standard methods. However, clinical adaptation will require external validation, interoperability with electronic health records, a clinicianfriendly design, and adherence to Good Machine Learning Practice. The lack of standardized comparator methods across studies remains a key limitation.

Ähnliche Arbeiten