Related Experiment Video
Updated: Jan 14, 2026
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Machine learning-based early prediction of asthma in preschoolers: The COCOA birth cohort study
Chang Hoon Han1,2, Seok-Jae Heo3, Haerin Jang4
1Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Korea.
Insights
Predicting preschool asthma is challenging. This study developed a machine learning model and a questionnaire-based tool, achieving high performance for early asthma prediction at age 3. Both methods identified key risk factors for timely intervention.
Area of Science:
- Pediatric Allergy and Immunology
- Computational Biology and Bioinformatics
- Epidemiology
Background:
- Early prediction of asthma in preschoolers is critical for effective intervention but remains a significant clinical challenge.
- This study addresses the need for improved diagnostic tools for identifying children at risk of developing asthma by age three.
Purpose of the Study:
- To develop and validate machine learning (ML)-based predictive models for asthma at age 3 years.
- To create and evaluate a questionnaire-based scoring tool for early asthma prediction, comparing its efficacy against ML models.
Main Methods:
- Utilized data from the COhort for Childhood Origin of Asthma and allergic diseases (COCOA) prospective birth cohort in South Korea.
- Developed Random Forest ML models using data up to age 2 years, employing LASSO regression for feature selection.
- Constructed and assessed a questionnaire-based scoring tool against multiple ML algorithms for predictive performance.
Main Results:
- ML models demonstrated increasing predictive accuracy with data accumulation, achieving an AUROC of 0.774 at 2 years.
- The questionnaire-based scoring tool showed comparable performance to ML models, with an AUROC of 0.790.
- Key predictors identified include paternal total IgE, maternal iron supplementation, parental asthma history, nut allergy, and recent lower respiratory infections.
Conclusions:
- Successfully developed robust and high-performing predictive models for early childhood asthma.
- The questionnaire-based tool presents significant clinical utility due to its ease of application.
- Further validation in diverse populations and research into identified predictor pathways are recommended to enhance clinical applicability.
Background:
Early prediction of asthma in preschoolers, which is crucial for timely intervention, remains challenging. This study aimed to develop a machine learning (ML)-based model and a questionnaire-based scoring tool for the prediction of asthma at age 3 years.
Methods:
Data from the COhort for Childhood Origin of Asthma and allergic diseases (COCOA), a comprehensive prospective birth cohort in South Korea, was used. Children with complete 3-year follow-up (n = 2007) were divided into development (n = 1472) and validation (n = 535) cohorts based on birth year. Asthma diagnosis at age 3 years was based on physician diagnosis, recurrent wheezing episodes, asthma treatment, or parental reports. Random Forest-based predictive models were developed using data collected until the age of 2 years, initially selecting features via least absolute shrinkage and selection operator (LASSO) regression. A questionnaire-based scoring tool was also developed and compared with multiple ML algorithms.
Results:
The ML-based prediction models showed improved performance as the data accumulated. The 6-month, 1-year, and 2-year models had area under the receiver operating characteristic curve (AUROC) values of 0.614, 0.726, and 0.774, respectively, in the validation cohort. The performance of the questionnaire-based scoring tool (AUROC, 0.790) was comparable to that of the ML-based model. Important predictors included paternal total IgE levels, maternal iron supplementation during pregnancy, parental asthma history, nut allergy history, and recent lower respiratory infections.
Conclusions:
Our study successfully developed robust predictive models for early asthma that demonstrated high performance. The questionnaire-based scoring tool offers particular value because of its clinical applicability. Further validation in diverse populations and investigation of the causative pathways of the identified predictors are necessary to enhance clinical utility.
Related Concept Videos
01:26Asthma-II: Pathophysiology and Classification
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include:
01:29Asthma-I: Introduction
01:30Asthma-IV: Diagnostic and Management
Clinical Assessment for Asthma:
This is the first step in diagnosing and managing asthma. It includes:
01:20Asthma: Pathogenesis and Management
Asthma is classified as allergic and non-allergic. Allergens such as dust mites, pollen, and pet dander trigger allergic asthma, while factors like cold air, intense emotions, or exercise can induce non-allergic asthma.
01:24Asthma-III: Symptoms and Complications
Classification of Asthma
01:24Antiasthma Drugs: Methylxanthines
Theophylline is thought to inhibit phosphodiesterase enzymes, increasing intracellular levels of cyclic adenosine monophosphate (cAMP) and cyclic guanosine monophosphate (cGMP). This rise in cAMP and cGMP concentrations stimulates cardiac function,...