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.

Primary care screening for childhood obesity: a population-based analysis.

BACKGROUND: The prevalence of obesity among children and adolescents in the western world has increased dramatically. OBJECTIVES: To assess the efficacy of routine childhood obesity screening by primary physicians in the pediatric population in Israel and the utilization of health services by overweight children. METHODS: The electronic medical records of children aged 60-83 months registered in 39 pediatric primary care centers between January 2001 and October 2004 (n=21,799) were reviewed. Those in whom height and weight were documented during a clinic visit (index visit) were classified as overweight, at risk of overweight, or normal weight according to body mass index percentiles. The number of visits to the pediatrician, laboratory tests and health care costs 12 months after the index visit were calculated. RESULTS: Anthropomorphic measurements were performed in 1556 of the 15,364 children (10.1%) who visited the clinic during the study period. Of these, 398 (25.6%) were overweight, 185 (11.9%) were at risk of overweight, and 973 (62.5%) were normal weight. Children in the first two groups visited the clinic slightly more often than the third group, but the differences were not statistically significant (P = 0.12), and they had significantly more laboratory tests than the rest of the children visiting the clinics (P = 0.053). Health care costs were 6.6% higher for the overweight than the normal-weight children. CONCLUSIONS: Electronic medical records are a useful tool for population-based health care assessments. Current screening for obesity in children during routine care in Israel is insufficient and additional education of community pediatricians in diagnosis and intervention is urgently needed.