EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Early predictors of persistent childhood asthma and allergic rhinitis: A machine learning study using post‐hoc explainability

Frederikke Rosenvinge Skov iD, Mario Lovrić iD, Tamo Sultan iD, Klaus Bønnelykke iD, Bo Chawes, Jakob Stokholm iD, Jonathan Thorsen iD, Morten Arendt Rasmussen, Ann-Marie Malby Schoos iD

Pediatric Allergy and Immunology · 2026-10 · 37 (10)

DOI: 10.1111/pai.70498 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Allergy and Immunology, online erschienen am 09.10.2026. Verfasst von Frederikke Rosenvinge Skov und 8 weiteren Autor:innen. Beteiligte Einrichtung: COPSAC, Copenhagen Prospective Studies on Asthma in Childhood, Copenhagen University Hospital-Herlev and Gentofte, Copenhagen, Denmark. Hauptthemen laut MEDLINE: Asthma, Rhinitis, Allergic, Machine Learning. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Lundbeck Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Asthma and allergic rhinitis (AR) follow heterogeneous childhood trajectories, and reliable early prediction of persistence or remission remains challenging. We investigated whether machine learning models applied to early‐life data could predict long‐term asthma and AR outcomes.

Methods

We analyzed data from 411 children in the Copenhagen Prospective Studies on Asthma in Childhood (COPSAC 2000 ) cohort using 113 early‐life clinical, genetic, environmental, immunological, and lung function features. Five machine learning models were trained to predict four outcomes: persistent asthma versus controls, persistent asthma versus asthma in remission, persistent AR versus controls, and teen‐onset AR versus controls. Model interpretability was assessed using SHapley Additive exPlanations (SHAP).

Results

Predictive performance was limited across all outcomes, and no model achieved an AUROC above 0.65. The highest performance was observed for persistent AR versus controls, where the tree‐based models performed similarly, with AUROCs around 0.63. For persistent asthma versus controls, Random Forest and XGBoost both achieved an AUROC of 0.59. Performance was weak for distinguishing persistent asthma from asthma in remission and for predicting teen‐onset AR, with the best models reaching AUROCs of 0.60 and 0.59, respectively. SHAP analyses of the best‐performing models identified biologically plausible features, including aeroallergen sensitization and genetic predisposition for persistent asthma, and familial, immunological, and growth‐related features for persistent AR, but these signals did not translate into strong discriminative performance.

Conclusion

In this deeply phenotyped high‐risk birth cohort, early‐life data analyzed using machine learning did not reliably predict long‐term asthma or AR outcomes. These findings suggest that early‐life data alone may be insufficient for individual prognostic stratification and that repeated measurements later in childhood may be needed to improve prediction. image

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AsthmaRhinitis, AllergicMachine LearningHumansFemaleChildPredictive Learning ModelsMaleAdolescentChild, PreschoolRandom ForestBoosting Machine Learning AlgorithmsPrognosisProspective StudiesPrediction AlgorithmsClassification AlgorithmsDenmark

Stichwörter der Autor:innen

allergicasthmaclinical aspectsearly interventionpediatricsrhinitisrisk factors

Autor:innen und Institutionen

  • COPSAC, Copenhagen Prospective Studies on Asthma in Childhood, Copenhagen University Hospital-Herlev and Gentofte, Copenhagen, Denmark.
  • Department of Pediatrics, Copenhagen University Hospital-Næstved, Slagelse and Ringsted, Slagelse, Denmark.
  • Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark.
  • Centre for Bioanthropology, Institute for Anthropological Research, Zagreb, Croatia.
  • Department of Food Science, University of Copenhagen, Copenhagen, Denmark.
  • Department of Pediatrics, Copenhagen University Hospital-Amager and Hvidovre, Hvidovre, Denmark.

ORCID-Profile: Frederikke Rosenvinge Skov, Mario Lovrić, Tamo Sultan, Klaus Bønnelykke, Jakob Stokholm, Jonathan Thorsen, Ann-Marie Malby Schoos

Förderung

  • Lundbeck Foundation

Zitieren

APA

Skov, F. R., Lovrić, M., Sultan, T., Bønnelykke, K., Chawes, B., Stokholm, J., Thorsen, J., Rasmussen, M. A., & Schoos, A. M. (2026). Early predictors of persistent childhood asthma and allergic rhinitis: A machine learning study using post‐hoc explainability. Pediatric Allergy and Immunology, 37(10). https://doi.org/10.1111/pai.70498

Vancouver

Skov FR, Lovrić M, Sultan T, Bønnelykke K, Chawes B, Stokholm J, et al. Early predictors of persistent childhood asthma and allergic rhinitis: A machine learning study using post‐hoc explainability. Pediatric Allergy and Immunology. 2026;37(10). doi:10.1111/pai.70498

BibTeX
@article{Skov2026,
  author = {Skov, Frederikke Rosenvinge and Lovrić, Mario and Sultan, Tamo and Bønnelykke, Klaus and Chawes, Bo and Stokholm, Jakob and Thorsen, Jonathan and Rasmussen, Morten Arendt and Schoos, Ann-Marie Malby},
  title = {Early predictors of persistent childhood asthma and allergic rhinitis: A machine learning study using post‐hoc explainability},
  journal = {Pediatric Allergy and Immunology},
  year = {2026},
  volume = {37},
  number = {10},
  doi = {10.1111/pai.70498}
}
Kostenlos starten →