Soriano-Arandes Antoni, Andrés Cristina, Perramon-Malavez Aida, Creus-Costa Anna, Gatell Anna, Martín-Martín Ramona, Solà-Segura Elisabet, Riera-Bosch Maria Teresa, Fernández Eduard, Biosca Mireia, Capdevila Ramon, Sánchez Almudena, Soler Isabel, Chiné Maria, Sanz Lidia, Quezada Gabriela, Pérez Sandra, Canadell Dolors, Salvadó Olga, Ridao Marisa, Sau Imma, Rifà Ma Àngels, Macià Esperança, Burgaya-Subirana Sílvia, Vila Mònica, Vila Jorgina, Mejías Asunción, Antón Andrés, Soler-Palacin Pere, Prats Clara
Pediatric Infectious Diseases and Immunodeficiencies Unit, Children's Hospital, Vall d'Hebron Barcelona Hospital Campus, 08035 Barcelona, Spain.
Infection and Immunity in Pediatric Patients, Vall d'Hebron Research Institute, 08035 Barcelona, Spain.
Viruses. 2025 Apr 8;17(4):546. doi: 10.3390/v17040546.
(1) Background: Respiratory viral infections, including those caused by SARS-CoV-2, respiratory syncytial virus (RSV), influenza viruses, rhinovirus, and adenovirus, are major causes of acute respiratory infections (ARIs) 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. (2) 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. (3) Results: The model performed better for RSV (AUC: 0.81, sensitivity: 0.64, specificity: 0.77) and influenza viruses (AUC: 0.71, sensitivity: 0.70, specificity: 0.59) 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. (4) Conclusions: The study demonstrated that symptom-based predictive models effectively identify pediatric respiratory infections, with notable accuracy for those caused by RSV, SARS-CoV-2, and influenza viruses.
（1）背景：呼吸道病毒感染，包括由严重急性呼吸综合征冠状病毒2（SARS-CoV-2）、呼吸道合胞病毒（RSV）、流感病毒、鼻病毒和腺病毒引起的感染，是儿童急性呼吸道感染（ARI）的主要原因。基于症状的预测模型是加快诊断的宝贵工具，尤其是在初级保健环境中。本研究使用症状数据评估了基于机器学习的模型在估计这些常见儿童呼吸道病毒感染概率方面的有效性。（2）方法：收集了2021年10月至2023年10月期间在14个初级保健中心（加泰罗尼亚儿科冠状病毒研究组（COPEDICAT）成员）评估的868名有ARI症状儿童的数据。使用具有10倍交叉验证的随机森林和提升模型，并应用合成少数过采样技术（SMOTE-NC）来解决类别不平衡问题。通过曲线下面积（AUC）、敏感性、特异性和用于特征重要性的夏普利值（SHAP）评估模型性能。（3）结果：该模型对RSV（AUC：0.81，敏感性：0.64，特异性：0.77）和流感病毒（AUC：0.71，敏感性：0.70，特异性：0.59）的表现较好，并且基于无啰音和喘息等症状有效排除了SARS-CoV-2。由于鼻病毒和腺病毒等非包膜病毒的症状不具特异性，其预测性能较低。SHAP分析确定了每种病毒的关键症状模式。（4）结论：该研究表明，基于症状的预测模型能有效识别儿童呼吸道感染，对由RSV、SARS-CoV-2和流感病毒引起的感染具有显著准确性。
