Artificial Intelligence in the Diagnosis and Management of Appendicitis in Pediatric Departments: A Systematic Review

dx.doi.org

Introduction Artificial intelligence (AI) is a growing field in medical research that could potentially help in the challenging diagnosis of acute appendicitis (AA) in children. However, usefulness of AI in clinical settings remains unclear. Our aim was to assess the accuracy of AIs in the diagnosis of AA in the pediatric population through a systematic literature review. Methods PubMed, Embase, and Web of Science were searched using the following keywords: “pediatric,” “artificial intelligence,” “standard practices,” and “appendicitis,” up to September 2023. The risk of bias was assessed using PROBAST. Results A total of 302 articles were identified and nine articles were included in the final review. Two studies had prospective validation, seven were retrospective, and no randomized control trials were found. All studies developed their own algorithms and had an accuracy greater than 90% or area under the curve >0.9. All studies were rated as a “high risk” concerning their overall risk of bias. Conclusion We analyzed the current status of AI in the diagnosis of appendicitis in children. The application of AI shows promising potential, but the need for more rigor in study design, reporting, and transparency is urgent to facilitate its clinical implementation.

dx.doi.org shows its articles on its own site.

Read the article on dx.doi.org ↗

Article · Feb 2024 · 1 min read

In brief

Systematic review evaluating AI algorithms for diagnosing acute appendicitis in children found nine studies with >90% accuracy, but all had high risk of bias due to predominantly retrospective designs and lack of prospective validation. While AI shows promise for this challenging pediatric diagnosis, rigorous prospective studies are needed before clinical implementation.

AI algorithms achieved >90% accuracy in diagnosing pediatric appendicitis, but all studies had high risk of bias.
Only 2 of 9 studies included prospective validation; no randomized controlled trials exist yet.
Current AI models are institution-specific with limited external validation, hindering clinical implementation.
Rigorous study design and transparent reporting are needed before AI can be reliably used in pediatric emergency departments.
AI shows promise for reducing diagnostic uncertainty in pediatric appendicitis but requires standardized validation frameworks.

Written by the GCMD Library team from the article.

Read it at the source ↗