Key result
Machine learning outperforms previous methods for detecting sleep apnea events with ~87% accuracy.
Why the study?
Manual evaluation of type I polysomnography for apneic events is time-consuming, costly, and prone to errors, motivating the use of artificial intelligence to assist clinical evaluations.
Does a machine learning-based approach accurately recognize apneic events in subjects with sleep apnea-hypopnea syndrome?
Does a machine learning-based approach accurately recognize apneic events in subjects with sleep apnea-hypopnea syndrome?
A machine learning approach using polysomnographic recordings achieved 87.2% accuracy in detecting sleep apnea events, outperforming previous methods on the Wisconsin Sleep Cohort database.
ML may enhance research automation of apnea detection; leaves open prospective validation before any clinical adoption.
Goal: The gold standard for detecting the presence of apneic events is a time and effort-consuming manual evaluation of type I polysomnographic recordings by experts, often not error-free. Such acquisition protocol requires dedicated facilities resulting in high costs and long waiting lists. The usage of artificial intelligence models assists the clinician's evaluation overcoming the aforementioned limitations and increasing healthcare quality. Methods: The present work proposes a machine learning-based approach for automatically recognizing apneic events in subjects affected by sleep apnea-hypopnea syndrome. It embraces a vast and diverse pool of subjects, the Wisconsin Sleep Cohort (WSC) database. Results: An overall accuracy of 87.2<tex-math notation="LaTeX">±</tex-math>1.8% is reached for the event detection task, significantly higher than other works in literature performed over the same dataset. The distinction between different types of apnea was also studied, obtaining an overall accuracy of 62.9<tex-math notation="LaTeX">±</tex-math>4.1%. Conclusions: The proposed approach for sleep apnea events recognition, validated over a wide pool of subjects, enlarges the landscape of possibilities for sleep apnea events recognition, identifying a subset of signals that improves State-of-the-art performance and guarantees simple interpretation.
No takes yet. Share an insight, caveat, or question.
Porta et al. (2024) studied Sleep apnea-hypopnea syndrome. Machine learning-based approach for automatically recognizing apneic events vs. Other works in literature was evaluated on Event detection task (recognizing apneic events). A machine learning-based approach achieved an overall accuracy of 87.2±1.8% for detecting sleep apnea events, significantly outperforming previous methods on the same dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: