Predicting polysomnographic severity thresholds in children using machine learning
Dylan Bertoni1, Laura M Sterni2, Kevin D Pereira1
1Department of Otorhinolaryngology-Head and Neck Surgery, University of Maryland School of Medicine, Baltimore, MD, USA.
Insights
Machine learning combined with wearable sensors accurately identifies children needing overnight monitoring after tonsillectomy and adenoidectomy. This approach offers a cost-effective screening method for obstructive sleep disordered breathing severity.
Area of Science:
- Pediatric Sleep Medicine
- Artificial Intelligence in Healthcare
- Wearable Technology
Background:
- Tonsillectomy and adenoidectomy (T&A) are common procedures for pediatric obstructive sleep disordered breathing (oSDB).
- Polysomnography is effective for risk stratification but is resource-intensive.
- A need exists for cost-effective methods to identify children requiring postoperative monitoring.
Purpose of the Study:
- To develop and validate machine learning models for identifying children with severe oSDB.
- To assess the utility of wearable sensor data (actigraphy and oximetry) for predicting polysomnography-derived severity.
- To establish a resource-conscious screening pathway for children undergoing T&A.
Main Methods:
- Machine learning models were developed using clinical data and sensor data (actigraphy, oximetry).
- Children aged 2-17 years undergoing polysomnography were included in the study.
- Model performance was evaluated based on predicting apnea-hypopnea index (AHI) severity.
Main Results:
- Clinical parameters alone showed poor predictive accuracy for AHI severity (AHI >2: 48-56%; AHI >10: 50-61%).
- Combining oximetry and actigraphy data significantly improved prediction accuracy.
- Accuracies reached 87-89% for AHI >2 and 95-96% for AHI >10 when using combined sensor data.
Conclusions:
- Machine learning utilizing oximetry and actigraphy effectively identifies children needing overnight monitoring based on oSDB severity.
- This approach supports a resource-conscious screening pathway for children undergoing T&A.
- The findings demonstrate the potential for a lower-cost, patient-friendly screening tool for severe obstructive sleep apnea syndrome in children.
Background:
Approximately 500,000 children undergo tonsillectomy and adenoidectomy (T&A) annually for treatment of obstructive sleep disordered breathing (oSDB). Although polysomnography is beneficial for preoperative risk stratification in these children, its expanded use is limited by the associated costs and resources needed. Therefore, we used machine learning and data from potentially wearable sensors to identify children needing postoperative overnight monitoring based on the polysomnographic severity of oSDB.
Methods:
Children aged 2-17 years undergoing polysomnography were included. Six machine learning models were created using (i) clinical parameters and (ii) nocturnal actigraphy and oxygen desaturation index. The prediction performance for polysomnography-derived severity of oSDB measured by apnea hypopnea index (AHI) >2 and >10 were evaluated.
Results:
One hundred and ninety children were included. One hundred and eight were male (57%), mean age was 6.7 years [95% confidence interval; 6.1, 7.2], and mean AHI was 10.6 [7.8, 13.4]. Predictive performance utilizing clinical parameters was poor for both AHI > 2 (accuracy range: 48-56% for all models) and AHI > 10 (50-61%). Combining oximetry and actigraphy improved the accuracy to 87-89% for AHI > 2 and 95-96% for AHI > 10.
Conclusions:
Machine learning with oximetry and actigraphy identifies most children needing overnight monitoring as determined by polysomnographic severity of oSDB, supporting a potential resource-conscious screening pathway for children undergoing T&A.
Impact:
We provide proof of principle for the utility of machine learning, oximetry, and actigraphy to screen for severe obstructive sleep apnea syndrome (OSAS) in children. Clinical parameters perform poorly in predicting the severity of OSAS, which is confirmed in the current study. The predictive accuracy for severe OSAS was improved by a smaller subset of quantifiable physiologic parameters, such as oximetry. The results of this study support a lower cost, patient-friendly screening pathway to identify children in need of in-hospital observation after surgery.
More Related Videos
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
08:20Measuring Neural Mechanisms Underlying Sleep-Dependent Memory Consolidation During Naps in Early Childhood
Published on: October 2, 2019