AI for pRedicting Exacerbations in KIDs with aSthma (AIRE-KIDS)

2025-11-02

AI Summary

This study addresses the challenge of early identification of high-risk children prone to severe asthma exacerbations—such as emergency department visits or hospitalizations—by integrating heterogeneous data sources: electronic health records, environmental pollutant exposures (e.g., PM₂.₅, NO₂), and neighborhood-level social vulnerability indices. We propose a novel multimodal predictive framework that synergistically combines gradient-boosted decision trees (LGBM/XGBoost) with lightweight large language models (DistilGPT2/Llama) for feature representation and fusion. Model interpretability is ensured via SHAP analysis to identify clinically and socially salient risk drivers. On an independent validation cohort, our model achieves an AUC of 0.712 and F1-score of 0.51—significantly outperforming current clinical guidelines (F1 = 0.334). Beyond improved predictive performance, the framework uncovers synergistic effects between environmental and socioeconomic determinants of asthma exacerbation, offering actionable, interpretable insights with direct potential for clinical deployment and public health intervention.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Recurrent exacerbations remain a common yet preventable outcome for many children with asthma. Machine learning (ML) algorithms using electronic medical records (EMR) could allow accurate identification of children at risk for exacerbations and facilitate referral for preventative comprehensive care to avoid this morbidity. We developed ML algorithms to predict repeat severe exacerbations (i.e. asthma-related emergency department (ED) visits or future hospital admissions) for children with a prior asthma ED visit at a tertiary care children's hospital. Retrospective pre-COVID19 (Feb 2017 - Feb 2019, N=2716) Epic EMR data from the Children's Hospital of Eastern Ontario (CHEO) linked with environmental pollutant exposure and neighbourhood marginalization information was used to train various ML models. We used boosted trees (LGBM, XGB) and 3 open-source large language model (LLM) approaches (DistilGPT2, Llama 3.2 1B and Llama-8b-UltraMedical). Models were tuned and calibrated then validated in a second retrospective post-COVID19 dataset (Jul 2022 - Apr 2023, N=1237) from CHEO. Models were compared using the area under the curve (AUC) and F1 scores, with SHAP values used to determine the most predictive features. The LGBM ML model performed best with the most predictive features in the final AIRE-KIDS_ED model including prior asthma ED visit, the Canadian triage acuity scale, medical complexity, food allergy, prior ED visits for non-asthma respiratory diagnoses, and age for an AUC of 0.712, and F1 score of 0.51. This is a nontrivial improvement over the current decision rule which has F1=0.334. While the most predictive features in the AIRE-KIDS_HOSP model included medical complexity, prior asthma ED visit, average wait time in the ED, the pediatric respiratory assessment measure score at triage and food allergy.

Problem

• Predict recurrent severe asthma exacerbations in children using ML algorithms
• Identify key predictive features from EMR data for asthma-related hospital visits
• Improve pediatric asthma care through early risk detection and intervention

Innovation

• Used machine learning to predict asthma exacerbations in children
• Leveraged electronic medical records and environmental data for modeling
• Applied boosted trees and large language models for analysis