Implementing Symptom-Based Predictive Models for Early Diagnosis of Pediatric Respiratory Viral Infections

Introduction: Respiratory viral infections, including SARS-CoV-2, respiratory syncytial virus (RSV), influenza, rhinovirus, and adenovirus, are major causes of acute respiratory illness (ARI) in children. Symptom-based predictive models are valuable tools for expediting diagnoses, particularly in primary care settings. This study assessed the effectiveness of machine learning-based models in estimating infection probabilities for these common pediatric respiratory viruses using symptom data. Methods: Data were collected from 868 children with ARI symptoms evaluated across 14 primary care centers, members of COPEDICAT (Coronavirus Pediatria Catalunya), from October 2021 to October 2023. Random Forest and Boosting models with 10-fold cross-validation were used, applying SMOTE-NC to address class imbalance. Model performance was evaluated via area under the curve (AUC), sensitivity, specificity, and Shapley Additive exPlanations (SHAP) values for feature importance. Results: The model performed best for RSV (AUC: 0.81, sensitivity: 0.64, specificity: 0.77) and effectively ruled out SARS-CoV-2 based on symptom absence, such as crackles and wheezing. Predictive performance was lower for non-enveloped viruses like rhinovirus and adenovirus, due to their nonspecific symptom profiles. SHAP analysis identified key symptoms patterns for each virus. Conclusions: The study demonstrated that symptom-based predictive models effectively identify pediatric respiratory infections, with notable accuracy for RSV, SARS-CoV-2 and influenza.