Truace
Subscribe

Diagnostic Accuracy of Artificial Intelligence versus Clinical Diagnosis in Detecting Acute Otitis Media: A Systematic Review and Meta-analysis

Abstract Acute otitis media (AOM) represents a prevalent infection in children globally, leading to considerable morbidity and imposing a substantial burden on healthcare systems. Prompt and precise diagnosis is critical to reducing complications, such as tympanic membrane perforation, hearing impairment, and excessive antibiotic prescribing. Advances in artificial intelligence (AI), particularly deep learning, have created opportunities to enhance diagnostic accuracy and broaden access to care, especially in lo…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-2182· cite & verify
Diagnostic Accuracy of Artificial Intelligence versus Clinical Diagnosis in Detecting Acute Otitis Media: A Systematic Review and Meta-analysis
Doctor Wenlock outside St Thomas's Hospital - geograph.org.uk - 3101668 by PAUL FARMER. CC BY-SA 2.0 · https://creativecommons.org/licenses/by-sa/2.0

In brief

Researchers pooled results from nine studies published between 2020 and 2025 that tested AI-based tools for diagnosing acute otitis media, a common childhood ear infection. Searches ran through July 2025, and the AI tools were judged against a clinical reference standard.

The findings suggest AI could support earlier and more accurate diagnosis, which matters because delayed or imprecise diagnosis can lead to complications and excess antibiotic use. The authors frame the benefit as potential, particularly for underserved regions, so real-world impact on access and outcomes is not demonstrated in this abstract.

Main points

  1. Nine studies from 2020 to 2025 met the inclusion criteria for the meta-analysis.
  2. Pooled sensitivity was 91% (95% CI 77%–97%) and pooled specificity was 99% (95% CI 94%–100%).
  3. AI models matched or outperformed general practitioners and pediatricians and approached otolaryngologist-level accuracy.
  4. The authors say AI could help narrow healthcare access gaps, especially in underserved regions.

The gain

Across nine studies, AI systems detected acute otitis media with pooled sensitivity of 91% and specificity of 99%, matching or beating general practitioners and pediatricians.

The rundown

The review followed PRISMA-DTA standards with PROSPERO registration and searched PubMed, Web of Science, and IEEE Xplore. Eligible studies enrolled human participants with suspected AOM, used AI-driven diagnosis, and relied on a clinical reference standard.

Risk of bias was assessed with the QUADAS-2 tool, and pooled accuracy was estimated with a bivariate random-effects model. The analysis also compared performance across different model architectures and diagnostic methods.

The abstract notes that AOM causes considerable morbidity and burdens health systems. Accurate diagnosis could reduce complications such as tympanic membrane perforation and hearing impairment, as well as excessive antibiotic prescribing.

Sources

  1. Peer-reviewedSaudi Journal of Otorhinolaryngology Head and Neck Surgery2026-10-22

The debate