Search reports, ask a question, or jump to a page.
The problem
Intervention: Machine learning algorithms (support vector machine, random forest, logistic regression) applied to analyze breath sounds for classification of asthma subtypes
Who it was tested with: 50 children with asthma: 30 with asthma in remission and 20 with cough variant asthma.
Experience from people who deliver programmes: stories, case studies and lessons learned. Valuable for understanding how and why, and for spotting what to test next, but not a measure of effect.
"machine learning techniques were applied to objectively classify and evaluate the breath sounds of pediatric asthma patients. Then logistic regression, random forest, and support vector machine algorithms were employed to train models and predict outcomes." This represents a diagnostic algorithm validation approach with classification of breath sounds as the outcome measure.
Small sample size of 50 children limits generalizability. No external validation cohort or comparison with clinical diagnosis by physicians reported. Single-site study with unclear population source.
Across countries and designs
1 study · 1 country
Classified by the Hub's AI
Not yet reviewed by a person. Model output is not AICS's view until reviewed.
claude-haiku-4-5-20251001 · synth-v1
