EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Antoni Soriano-Arandes iD, Cristina Andrés, Aida Perramon-Malavez iD, Anna Creus-Costa iD, Anna Gatell, Ramona Martín-Martín, Elisabet Solà-Segura, Maria Teresa Riera-Bosch, Eduard Fernández, Mireia Biosca iD, Ramon Capdevila, Almudena Sánchez und 18 weitere

Viruses · 2025

DOI: 10.3390/v17040546 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Viruses, 2025. Verfasst von Antoni Soriano-Arandes und 29 weiteren Autor:innen. Beteiligte Einrichtung: Pediatric Infectious Diseases and Immunodeficiencies Unit, Children's Hospital, Vall d'Hebron Barcelona Hospital Campus, 08035 Barcelona, Spain. Hauptthemen laut MEDLINE: Respiratory Tract Infections, Virus Diseases. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundació La Marató tv3.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

(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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Respiratory Tract InfectionsVirus DiseasesHumansInfantMaleChild, PreschoolFemaleChildEarly DiagnosisCOVID-19Machine LearningInfluenza, HumanSARS-CoV-2Sensitivity and SpecificityRespiratory Syncytial Virus InfectionsRhinovirus

Stichwörter der Autor:innen

acute respiratory infectionpediatric carerespiratory virus infectionssymptom-based predictive modelingtriage

Autor:innen und Institutionen

  • 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.
  • Respiratory Virus Unit, Microbiology Department, Vall d'Hebron Research Institute, Vall d'Hebron University Hospital, Vall d'Hebron Barcelona Hospital Campus, 08035 Barcelona, Spain.
  • Computational Biology and Complex Systems (BIOCOM-SC) Group, Department of Physics, Barcelona School of Agri-Food and Biosystems Engineering, Universitat Politècnica de Catalunya, 08860 Castelldefels, Spain.
  • Department of Pediatrics, Children's Hospital, Vall d'Hebron Barcelona Hospital Campus, 08035 Barcelona, Spain.
  • Equip Pediatria Territorial Garraf, 08812 Barcelona, Spain.

ORCID-Profile: Antoni Soriano-Arandes, Aida Perramon-Malavez, Anna Creus-Costa, Mireia Biosca, Sílvia Burgaya-Subirana, Asunción Mejías, Pere Soler-Palacin, Clara Prats

Förderung

  • Fundació La Marató tv3

Zitieren

APA

Soriano-Arandes, A., Andrés, C., Perramon-Malavez, A., Creus-Costa, A., Gatell, A., Martín-Martín, R., Solà-Segura, E., Riera-Bosch, M. T., Fernández, E., Biosca, M., Capdevila, R., Sánchez, A., Soler, I., Chiné, M., Sanz, L., Quezada, G., Pérez, S., Canadell, D., Salvadó, O., …, & Prats, C. (2025). Implementing Symptom-Based Predictive Models for Early Diagnosis of Pediatric Respiratory Viral Infections. Viruses. https://doi.org/10.3390/v17040546

Vancouver

Soriano-Arandes A, Andrés C, Perramon-Malavez A, Creus-Costa A, Gatell A, Martín-Martín R, et al. Implementing Symptom-Based Predictive Models for Early Diagnosis of Pediatric Respiratory Viral Infections. Viruses. 2025. doi:10.3390/v17040546

BibTeX
@article{SorianoArandes2025,
  author = {Soriano-Arandes, Antoni and Andrés, Cristina and Perramon-Malavez, Aida and Creus-Costa, Anna and Gatell, Anna and Martín-Martín, Ramona and Solà-Segura, Elisabet and Riera-Bosch, Maria Teresa and Fernández, Eduard and Biosca, Mireia and Capdevila, Ramon and Sánchez, Almudena and Soler, Isabel and Chiné, Maria and Sanz, Lidia and Quezada, Gabriela and Pérez, Sandra and Canadell, Dolors and Salvadó, Olga and Ridao, Marisa and Sau, Imma and Rifà, Ma Àngels and Macià, Esperança and Burgaya-Subirana, Sílvia and Vila, Mònica and Vila, Jorgina and Mejías, Asunción and Antón, Andrés and Soler-Palacin, Pere and Prats, Clara},
  title = {Implementing Symptom-Based Predictive Models for Early Diagnosis of Pediatric Respiratory Viral Infections},
  journal = {Viruses},
  year = {2025},
  doi = {10.3390/v17040546}
}
Kostenlos starten →