Novel AI tool for diagnosis of acute otitis media

Content Editor: Dr. Prachi Goswami

March 13, 2024 at 2:45:00 PM

AI in Healthcare, Diagnostic tests, Infections

Acute otitis media is one of the most common ear conditions in children for which antibiotics are prescribed.
Its diagnosis is mostly clinical but diagnostic accuracy is low overall leading to inappropriate antibiotic usage.
A new AI tool using a deep residual-recurrent neural network algorithm has been developed at the University of Pittsburgh, US.
The tool has a sensitivity of 93.8% (95% confidence interval [CI], 92.6% to 95.0%) and a specificity of 93.3% (95% CI, 92.5% to 94.1%).
This could help in use by trained paramedical staff, documentation for records, and discussion with parents.
Improved diagnosis can help reduce inappropriate use of antimicrobials for this common condition.
The drawbacks of the study include the following:

The selection of the training and testing data
The gold standard used for comparison was the opinion of the expert otoscopists, rather than myringotomy and tympanocentesis (since they are invasive procedures).