Smartphone-based Detection of Group A Streptococcal Pharyngitis in Ugandan Children: A Pilot Study

Area of Science:

• Medical Diagnostics
• Artificial Intelligence in Medicine
• Public Health

Background:

• Prompt diagnosis of Group A Streptococcus (GAS) pharyngitis is crucial for preventing acute rheumatic fever and rheumatic heart disease.
• Current point-of-care diagnostics are often unaffordable and inaccessible in low-resource settings.

Purpose of the Study:

• To evaluate the efficacy of a smartphone-based artificial intelligence (AI) tool for diagnosing GAS pharyngitis.
• To assess the potential of this technology as a low-cost diagnostic in resource-limited, rheumatic heart disease-endemic regions.

Main Methods:

• A prospective study was conducted in Uganda involving children aged 5-15 presenting with sore throat.
• Oropharyngeal videos were captured via smartphone and analyzed by an AI image recognition model.
• The AI model was trained and validated using combined data from Ugandan and US cohorts, with microbiologic culture as the reference standard.

Main Results:

• The AI-powered smartphone approach demonstrated high diagnostic accuracy.
• Sensitivity was 100% (95% CI: 73.5%-100%), specificity was 95.7% (95% CI: 88.0%-99.1%), and overall accuracy was 96.6% (95% CI: 90.0%-99.3%).
• The area under the receiver operating curve was 0.93 (95% CI: 0.83-1.00).

Conclusions:

• Smartphone-based AI shows significant potential as a rapid, noninvasive diagnostic tool for GAS pharyngitis.
• This technology could be instrumental in the primary prevention of rheumatic heart disease in endemic settings.
• The findings support the use of accessible AI diagnostics in low-resource healthcare environments.