Machine Learning for Clinical Decision Support of Acute Streptococcal Pharyngitis: A Pilot Study.

Background: Group A Streptococcus (GAS) is the predominant bacterial pathogen of pharyngitis in children. However, distinguishing GAS from viral pharyngitis is sometimes difficult. Unnecessary antibiotic use contributes to unwanted side effects, such as allergic reactions and diarrhea. It also may increase antibiotic resistance.

Objectives: To evaluate the effect of a machine learning algorithm on the clinical evaluation of bacterial pharyngitis in children.

Methods: We assessed 54 children aged 2-17 years who presented to a primary healthcare clinic with a sore throat and fever over 38°C from 1 November 2021 to 30 April 2022. All children were tested with a streptococcal rapid antigen detection test (RADT). If negative, a throat culture was performed. Children with a positive RADT or throat culture were considered GAS-positive and treated antibiotically for 10 days, as per guidelines. Children with negative RADT tests throat cultures were considered positive for viral pharyngitis. The children were allocated into two groups: Group A streptococcal pharyngitis (GAS-P) (n=36) and viral pharyngitis (n=18). All patients underwent a McIsaac score evaluation. A linear support vector machine algorithm was used for classification.

Results: The machine learning algorithm resulted in a positive predictive value of 80.6 % (27 of 36) for GAS-P infection. The false discovery rates for GAS-P infection were 19.4 % (7 of 36).

Conclusions: Applying the machine-learning strategy resulted in a high positive predictive value for the detection of streptococcal pharyngitis and can contribute as a medical decision aid in the diagnosis and treatment of GAS-P.