Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2182
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-22T22:01:56.589113Z
status: published
lens: g_space
sector: health
headline: Diagnostic Accuracy of Artificial Intelligence versus Clinical Diagnosis in Detecting Acute Otitis Media: A Systematic Review and Meta-analysis
dek: 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…
gain_title: 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.
problem_title: (none)
trace_subject: (none)
gain_reading: 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.
gain_evidence: The pooled sensitivity and specificity were 91% (95% confidence interval [CI]: 77%–97%) and 99% (95% CI: 94%–100%), respectively. | AI models overall matched or outperformed general practitioners and pediatricians, approaching otolaryngologist-level accuracy.
problem_reading: (none)
problem_evidence: (none)
quick_read: 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.
limitation: The pooled sensitivity estimate has a wide confidence interval (77%–97%), and the evidence base is only nine studies, so the precision and generalizability of the performance estimate are uncertain.
tag: Evidence-backed gain
key_points: Nine studies from 2020 to 2025 met the inclusion criteria for the meta-analysis. | Pooled sensitivity was 91% (95% CI 77%–97%) and pooled specificity was 99% (95% CI 94%–100%). | AI models matched or outperformed general practitioners and pediatricians and approached otolaryngologist-level accuracy. | The authors say AI could help narrow healthcare access gaps, especially in underserved regions.
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:
- peer_reviewed | Saudi Journal of Otorhinolaryngology Head and Neck Surgery | https://doi.org/10.4103/sjoh.sjoh_134_25 | 2026-10-22
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

2a268a7830fbee73e8c1999929d21627fb3fb9f65849447a37804f4fd8ed1610

previous

0000000000000000000000000000000000000000000000000000000000000000