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.
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.
Objective:
Infants hospitalized with bronchiolitis may experience persistent symptoms linked to future chronic lung diseases like bronchiectasis. Identifying phenotypes during hospitalization could guide targeted interventions. As traditional clustering requires large datasets, this study explores whether Unsupervised Feature Extraction Algorithms (UFEAs) and clustering can identify high-risk profiles in a small dataset of Indigenous infants.
Methods:
We included 128 Indigenous infants hospitalized with bronchiolitis at the Royal Darwin Hospital, Northern Territory, Australia. Eight UEFAs were applied to reduce the dimensionality of 22 variables across 2-17 dimensions. A support vector machine classifier assessed the effectiveness of each UFEA in classifying bronchiectasis. Kernel Principal Component Analysis with nine dimensions performed best, and these dimensions were used for clustering.
Results:
Six clinical profiles were identified. Profile C, the highest-risk group with the most infants with bronchiectasis (45%), preterm birth (95%), low birth weight (86%), weight-for-length z-score < -2 (62%), household smoke exposure (90%), and antibiotics prescribed before hospitalization (100%). Profile D, the second-highest risk, had bronchiectasis (30%), the highest wet/productive cough (45%), crackles/crepitations (36%), and wheeze (18%). Profile F infants included bronchiectasis (22%), oxygen supplementation (91%), and lobar collapse/consolidation on chest X-rays (65%). Profile A included bronchiectasis (5%) and household smoke exposure (30%), and Profile E showed bronchiectasis (9%) and household smoke exposure (36%). Profile B, the lowest-risk group, with no bronchiectasis (0%), preterm birth (15%), low birth weight (10%), and any bacteria (5%).
Conclusion:
Using UFEAs and clustering, we reduced dataset dimensionality, effectively identifying six unique, clinically significant risk profiles in Indigenous infants.
More Related Videos
05:31Noninvasive Sampling of Mucosal Lining Fluid for the Quantification of In Vivo Upper Airway Immune-mediator Levels
Published on: August 7, 2017
09:21Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons
Published on: July 7, 2023
