MSED: a multi-modal sleep event detection model for clinical sleep analysis
This work provides an incremental improvement for clinicians by offering a more consistent and potentially efficient method for detecting sleep events, which are crucial for diagnosing sleep disorders.
This paper addresses the problem of automating the detection of sleep events (arousals, leg movements, and sleep-disordered breathing) from polysomnograms to reduce variability in clinical sleep analysis. The authors developed a single deep neural network that jointly detects these events, achieving F1 scores of 0.70 for arousals, 0.63 for leg movements, and 0.62 for sleep-disordered breathing, outperforming separate models.
Study objective: Clinical sleep analysis require manual analysis of sleep patterns for correct diagnosis of sleep disorders. Several studies show significant variability in scoring discrete sleep events. We wished to investigate, whether an automatic method could be used for detection of arousals (Ar), leg movements (LM) and sleep disordered breathing (SDB) events, and if the joint detection of these events performed better than having three separate models. Methods: We designed a single deep neural network architecture to jointly detect sleep events in a polysomnogram. We trained the model on 1653 recordings of individuals, and tested the optimized model on 1000 separate recordings. The performance of the model was quantified by F1, precision, and recall scores, and by correlating index values to clinical values using Pearson's correlation coefficient. Results: F1 scores for the optimized model was 0.70, 0.63, and 0.62 for Ar, LM, and SDB, respectively. The performance was higher, when detecting events jointly compared to corresponding single-event models. Index values computed from detected events correlated well with manual annotations ($r^2$ = 0.73, $r^2$ = 0.77, $r^2$ = 0.78, respectively). Conclusion: Detecting arousals, leg movements and sleep disordered breathing events jointly is possible, and the computed index values correlates well with human annotations.