Clinical Profile Identification of Indigenous Infants With Bronchiolitis Through Using Unsupervised Feature

Hongqi Niu1, Gabrielle Britt McCallum2, Anne Bernadette Chang2,3

  • 1Faculty of Science and Technology, Charles Darwin University, Darwin, Northern Territory, Australia.

Pediatric Pulmonology
|January 7, 2026
PubMed

Insights

Unsupervised Feature Extraction Algorithms identified six distinct risk profiles in Indigenous infants hospitalized with bronchiolitis, aiding in early detection of chronic lung disease risks.

Area of Science:

  • Pediatric Pulmonology
  • Data Science in Healthcare
  • Indigenous Health Research

Background:

  • Infants hospitalized for bronchiolitis face risks of persistent symptoms and future chronic lung diseases like bronchiectasis.
  • Identifying high-risk infants early can enable targeted interventions and improve long-term outcomes.
  • Traditional clustering methods require large datasets, posing challenges for smaller cohorts like Indigenous infants.

Purpose of the Study:

  • To explore the utility of Unsupervised Feature Extraction Algorithms (UFEAs) combined with clustering for identifying high-risk phenotypes in a small dataset of Indigenous infants hospitalized with bronchiolitis.
  • To assess if UFEAs can effectively reduce data dimensionality for risk profiling in this specific population.

Main Methods:

  • A cohort of 128 Indigenous infants hospitalized with bronchiolitis was analyzed.
  • Eight UFEAs were applied to 22 variables to reduce dimensionality (2-17 dimensions).
  • Kernel Principal Component Analysis (KPCA) achieved the best dimensionality reduction (9 dimensions), which were then used for clustering to identify distinct infant profiles.

Main Results:

  • Six distinct clinical risk profiles were identified using UFEAs and clustering.
  • The highest-risk profile (Profile C) showed high rates of bronchiectasis (45%), preterm birth (95%), low birth weight (86%), and household smoke exposure (90%).
  • Other identified profiles indicated varying levels of bronchiectasis risk, cough severity, oxygen need, and consolidation, highlighting diverse clinical presentations.

Conclusions:

  • UFEAs and clustering effectively reduced data dimensionality, enabling the identification of six clinically significant risk profiles in Indigenous infants.
  • This approach offers a viable method for risk stratification in smaller datasets, potentially guiding early interventions for infants at risk of chronic lung disease.
Abstract