Related Experiment Video
Updated: Aug 8, 2025
Biaxial Mechanical Characterizations of Atrioventricular Heart Valves
Published on: April 9, 2019
Development and validation of moderate to severe obstructive sleep apnea screening test (ColTon) in a pediatric
Plamen Bokov1, Benjamin Dudoignon1, Imene Boujemla2
1Université de Paris-Cité, AP-HP, Hôpital Robert Debré, Service de Physiologie Pédiatrique-Centre du Sommeil, INSERM NeuroDiderot, F-75019, Paris, France; INSERM NeuroDiderot, F-75019, Paris, France.
Insights
A new machine learning algorithm accurately predicts moderate to severe obstructive sleep apnea syndrome (OSAS) in children. The ColTon index, using pharyngeal collapsibility and tonsillar hypertrophy, shows promise for early diagnosis in pediatric patients.
Area of Science:
- Pediatric Sleep Medicine
- Machine Learning in Healthcare
- Respiratory Disorders
Background:
- Obstructive sleep apnea syndrome (OSAS) is a significant health concern in children.
- Accurate prediction of moderate to severe OSAS is crucial for timely intervention.
- Existing diagnostic methods can be resource-intensive.
Purpose of the Study:
- To develop and validate a machine learning algorithm for predicting moderate to severe OSAS in children.
- To identify key predictors for OSAS in a pediatric population.
- To assess the algorithm's performance using external validation.
Main Methods:
- Utilized a large cross-sectional dataset of children with sleep-disordered breathing.
- Employed multivariable logistic regression and the cforest algorithm.
- Split data into training and testing sets (2:1 ratio) for development and external validation.
- Included clinical examination, acoustic rhinometry, pharyngometry, and parental questionnaires.
Main Results:
- The study included 336 children; 32% had moderate to severe OSAS.
- A machine learning algorithm (cforest) using the ColTon index (pharyngeal collapsibility and tonsillar hypertrophy) achieved an AUC of 0.89.
- The ColTon index demonstrated 76% accuracy, 63% sensitivity, and 81% specificity on the validation set.
Conclusions:
- A cforest classifier provides valid predictions for moderate to severe OSAS in children.
- The ColTon index is a promising tool for predicting OSAS in pediatric patients, particularly those who are obese.
- This machine learning approach can aid in the early identification and management of pediatric OSAS.
Objective:
Development and validation of a machine learning algorithm to predict moderate to severe obstructive sleep apnea syndrome (OSAS) in otherwise healthy children.
Design:
Multivariable logistic regression and cforest algorithm of a large cross-sectional data set of children with sleep-disordered breathing.
Setting:
An university pediatric sleep centre.
Participants:
Children underwent clinical examination, acoustic rhinometry and pharyngometry, and surveying through parental sleep questionnaires, allowing the recording of 14 predictors that have been associated with OSAS. The dataset was nonrandomly split into a training (development) versus test (external validation) set (2:1 ratio) based on the time of the polysomnography. We followed the TRIPOD checklist.
Results:
We included 336 children in the analysis: 220 in the training set (median age [25th-75th percentile]: 10.6 years [7.4; 13.5], z-score of BMI: 1.96 [0.73; 2.50], 89 girls) and 116 in the test set (10.3 years [7.8; 13.0], z-score of BMI: 1.89 [0.61; 2.46], 51 girls). The prevalence of moderate to severe OSAS was 106/336 (32%). A machine learning algorithm using the cforest with pharyngeal collapsibility (pharyngeal volume reduction from sitting to supine position measured by pharyngometry) and tonsillar hypertrophy (Brodsky scale), constituting the ColTon index, as predictors yielded an area under the curve of 0.89, 95% confidence interval [0.85-0.93]. The ColTon index had an accuracy of 76%, sensitivity of 63%, specificity of 81%, negative predictive value of 84%, and positive predictive value of 59% on the validation set.
Conclusion:
A cforest classifier allows valid predictions for moderate to severe OSAS in mostly obese, otherwise healthy children.
