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

Abstract

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 ageand 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.

The treatment efficacy of pharmacotherapies for rapid eye movement sleep behavior disorder with polysomnography evaluation: A systematic review and meta-analysis

“…Brink-Kjaer A et al. [ 54 ] used end-to-end deep neural networks to analyze PSG and presented an automatic and interpretable diagnostic tool for RBD. Rechichi I et al.…”

Too little or too much nocturnal movements in Parkinson’s disease: A practical guide to managing the unseen

“…In addition, EMG findings from limbs may provide crucial information that may help with diagnosis, understanding the evolution of RBD, and developing future treatment. This is an area in which artificial intelligence may have a potential role in terms of automating and interpreting complex V-PSG data [91] .…”