Arousal Characteristics in Patients with Parkinson's Disease and Isolated Rapid Eye Movement Sleep Behavior Disorder

Clinical neurophysiology of REM parasomnias: Diagnostic aspects and insights into pathophysiology

Parasomnias are due to a transient unstable state dissociation during entry into sleep, within sleep, or during arousal from sleep, and manifest with abnormal sleep related behaviors, perceptions, emotions, dreams, and autonomic nervous system activity. Rapid eye movement (REM) parasomnias include REM sleep behavior disorder (RBD), isolated recurrent sleep paralysis and nightmare disorder. Neurophysiology is key for diagnosing these disorders and provides insights into their pathophysiology. RBD is very well characterized from a neurophysiological point of view, also thank to the fact that polysomnography is needed for the diagnosis. Diagnostic criteria are provided by the American Academy of Sleep Medicine and video-polysomnography guidelines for the diagnosis by the International REM Sleep Behavior Disorder Study Group. Differences between the two sets of criteria are presented and discussed. Availability of polysomnography in RBD provides data on sleep electroencephalography (EEG), electrooculography (EOG) and electromyography (EMG). Sleep EEG in RBD shows e.g. changes in delta and theta power, in sleep spindles and K complexes. EMG during REM sleep is essential for RBD diagnosis and is an important neurodegeneration biomarker. RBD patients present alterations also in wake EEG, autonomic function, evoked potentials, and transcranial magnetic stimulation. Clinical neurophysiological data on recurrent isolated sleep paralysis and nightmare disorder are scant. The few available data provide insights into the pathophysiology of these disorders, demonstrating a state dissociation in recurrent isolated sleep paralysis and suggesting alterations in sleep macro- and microstructure as well as autonomic changes in nightmare disorder.

SViT: A Spectral Vision Transformer for the Detection of REM Sleep Behavior Disorder

REM sleep behavior disorder (RBD) is a parasomnia with dream enactment and presence of REM sleep without atonia (RSWA). RBD diagnosed manually via polysomnography (PSG) scoring, which is time intensive. Isolated RBD (iRBD) is also associated with a high probability of conversion to Parkinson's disease. Diagnosis of iRBD is largely based on clinical evaluation and subjective PSG ratings of REM sleep without atonia. Here we show the first application of a novel spectral vision transformer (SViT) to PSG signals for detection of RBD and compare the results to the more conventional convolutional neural network architecture. The vision-based deep learning models were applied to scalograms (30 or 300 s windows) of the PSG data (EEG, EMG and EOG) and the predictions interpreted. A total of 153 RBD (96 iRBD and 57 RBD with PD) and 190 controls were included in the study and 5-fold bagged ensemble was used. Model outputs were analyzed per-patient (averaged), with regards to sleep stage, and the SViT was interpreted using integrated gradients. Models had a similar per-epoch test F1 score. However, the vision transformer had the best per-patient performance, with an F1 score 0.87. Training the SViT on channel subsets, it achieved an F1 score of 0.93 on a combination of EEG and EOG. EMG is thought to have the highest diagnostic yield, but interpretation of our model showed that high relevance was placed on EEG and EOG, indicating these channels could be included for diagnosing RBD.

MSED: A Multi-Modal Sleep Event Detection Model for Clinical Sleep Analysis

Clinical sleep analysis require manual analysis of sleep patterns for correct diagnosis of sleep disorders. However, several studies have shown significant variability in manual scoring of clinically relevant discrete sleep events, such as arousals, leg movements, and sleep disordered breathing (apneas and hypopneas). We investigated whether an automatic method could be used for event detection and if a model trained on all events (joint model) performed better than corresponding event-specific models (single-event models). We trained a deep neural network event detection model on 1653 individual recordings and tested the optimized model on 1000 separate hold-out recordings. F1 scores for the optimized joint detection model were 0.70, 0.63, and 0.62 for arousals, leg movements, and sleep disordered breathing, respectively, compared to 0.65, 0.61, and 0.60 for the optimized single-event models. Index values computed from detected events correlated positively with manual annotations (r2 = 0.73, r2 = 0.77, r2 = 0.78, respectively). We furthermore quantified model accuracy based on temporal difference metrics, which improved overall by using the joint model compared to single-event models. Our automatic model jointly detects arousals, leg movements and sleep disordered breathing events with high correlation with human annotations. Finally, we benchmark against previous state-of-the-art multi-event detection models and found an overall increase in F1 score with our proposed model despite a 97.5% reduction in model size.

Sleep stability in isolated rapid eye movement sleep behavior disorder, Parkinson's disease, and dementia with Lewy bodies

BACKGROUND

Non-REM sleep symptoms remain poorly understood in alpha-synucleinopathies.

AIMS

The aims of the study were to compare sleep stability and transitions, arousals, and sleep cycle structure between isolated rapid eye movement (REM) sleep behavior disorder (iRBD), Parkinson's disease (PD), and dementia with Lewy Bodies (DLB).

MATERIALS AND METHODS

Sleep transition and stability measures were assessed in one-night video-polysomnography records. Transition measures were the number of shifts between Wake and REM, Wake and NREM, and REM and NREM. Stability measures were the number of passages within the same sleep stage. We assessed arousals, the number/duration of sleep cycles (defined as a sequence of any NREM stage to REM), and the duration of N3 and REM sleep in each cycle. These variables were compared between two sets of groups (PD vs. DLB vs. iRBD and RDB+ vs. RBD-).

RESULTS

We assessed 54 PD, 24 DLB, and 21 iRBD patients (54 RBD+, 22 RBD-). There were no significant differences regarding sleep stability measures. Arousal indices in N1 and N2 stages were significantly higher in PD compared with iRBD. 24% of the sample did not have any sleep cycle. PD had significantly fewer cycles than iRBD. Differences became non-significant when adjusting for medication. There was no effect of group or time of night in REM or N3 duration. There were no significant differences between RBD+ and RBD-.

DISCUSSION

There were no significant differences in stability/transition measures. Arousals and disturbance in sleep cycling were higher in PD, but the difference was no longer significant after adjusting for medication.

CONCLUSION

Different alpha-synucleinopathies have a similar degree of non-REM sleep instability, but medication could worsen symptoms in PD.

End-to-end Deep Learning of Polysomnograms for Classification of REM Sleep Behavior Disorder

Rapid eye movement (REM) sleep behavior disorder (RBD) is parasomnia and a prodromal manifestation of Parkinson's disease. The current diagnostic method relies on manual scoring of polysomnograms (PSGs), a procedure that is time and effort intensive, subject to interscorer variability, and requires high level of expertise. Here, we present an automatic and interpretable diagnostic tool for RBD that analyzes PSGs using end-to-end deep neural networks. We optimized hierarchical attention networks in a 5-fold cross validation directly to classify RBD from PSG data recorded in 143 participants with RBD and 147 age-and sex-matched controls. An ensemble model using logistic regression was implemented to fuse decisions from networks trained in various signal combinations. We interpreted the networks using gradient SHAP that attribute relevance of input signals to model decisions. The ensemble model achieved a sensitivity of 91.4 % and a specificity of 86.3 %. Interpretation showed that electroencephalography (EEG) and leg electromyography (EMG) exhibited most patterns with high relevance. This study validates a robust diagnostic tool for RBD and proposes an interpretable and fully automatic framework for end-to-end modeling of other sleep disorders from PSG data. Clinical relevance- This study presents a novel diagnostic tool for RBD that considers neurophysiologic biomarkers in multiple modalities.