Diagnostic modalities in pediatric obstructive sleep apnea: A review article
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Alternative tools like questionnaires and smartphone video analysis can effectively screen for pediatric obstructive sleep apnea (OSA). Automated oximetry and AI models offer accurate diagnosis when polysomnography is inaccessible.
Area Of Science
- Pediatric Sleep Medicine
- Diagnostic Technologies
- Respiratory Medicine
Background
- Pediatric obstructive sleep apnea (OSA) affects approximately 3% of children, leading to significant neurocognitive, behavioral, and cardiovascular issues.
- Polysomnography (PSG) is the standard diagnostic method but is often limited by accessibility.
- This review critically examines alternative diagnostic tools for pediatric OSA, evaluating their accuracy, feasibility, and clinical utility.
Purpose Of The Study
- To systematically review and synthesize evidence on alternative diagnostic tools for pediatric obstructive sleep apnea (OSA).
- To assess the accuracy, feasibility, and clinical applicability of non-PSG diagnostic methods in children.
- To identify optimal diagnostic pathways for pediatric OSA when PSG is not readily available.
Main Methods
- A systematic-narrative hybrid review was conducted using major scientific databases (PubMed, Scopus, Web of Science) up to July 2025.
- Studies included children aged 0-18 years diagnosed using questionnaires, oximetry, portable monitors, AI/ML models, or smartphone video analysis, compared against PSG.
- Five main categories of alternative diagnostic modalities were identified and evaluated.
Main Results
- Screening tools like the Pediatric Sleep Questionnaire (PSQ) and smartphone video analysis (VAPS) showed high sensitivity (73-96%) for OSA detection.
- Algorithm-enhanced pulse oximetry demonstrated excellent diagnostic accuracy (AUC 0.90-0.97, sensitivity/specificity >85-90%) for moderate-to-severe OSA.
- Machine learning models and wearables approached PSG-level performance, with stepwise screening combining questionnaires and oximetry proving optimal.
Conclusions
- Questionnaires and smartphone video analysis serve as effective screening tools for pediatric OSA in resource-limited settings.
- Automated oximetry and machine learning models provide viable diagnostic alternatives for moderate-to-severe pediatric OSA.
- Implementing tiered diagnostic pathways integrating various tools can enhance detection rates and reduce reliance on PSG.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.