TY - JOUR

T1 - SViT

T2 - a Spectral Vision Transformer for the Detection of REM Sleep Behavior Disorder

AU - Gunter, Katarina Mary

AU - Brink-Kjar, Andreas

AU - Mignot, Emmanuel

AU - Sorensen, Helge B.D.

AU - During, Emmanuel

AU - Jennum, Poul

N1 - Publisher Copyright: IEEE

PY - 2023

Y1 - 2023

N2 - 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 second 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.

AB - 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 second 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.

KW - Brain modeling

KW - Computational modeling

KW - Computer vision

KW - deep learning

KW - Electroencephalography

KW - Electrooculography

KW - Parkinson's disease

KW - polysomnography

KW - Rapid eye movement sleep

KW - RBD

KW - Sleep

KW - Transformers

KW - vision transformer

UR - http://www.scopus.com/inward/record.url?scp=85164386707&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2023.3292231

DO - 10.1109/JBHI.2023.3292231

M3 - Journal article

C2 - 37402190

AN - SCOPUS:85164386707

VL - 27

SP - 4285

EP - 4292

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 9

ER -