Spatiotemporal characteristics of cortical activities of REM sleep behavior disorder revealed by explainable machine learning using 3D convolutional neural network

Kim, Hyun; Seo, Pukyeong; Byun, Jung-Ick; Jung, Ki Young; Kim, Kyung Hwan

doi:10.1038/s41598-023-35209-1

Cited by 6 publications

(1 citation statement)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of RBD topics that were not covered in this review due to space limitations have recently been reported and reviewed [9,75,84]. Some of these topics include RBD in children, adolescents, and adults under 50 years old; acute RBD; stress disorders and RBD; gut microbiome dysbiosis in RBD [85]; abnormal activation of motor cortical network during phasic REM sleep in iRBD [86]; NREM sleep EEG oscillations in iRBD [87]; altered resting-state thalamo-occipital functional connectivity in iRBD [88]; quantitative actigraphic assessment of treatment response in RBD [89]; digital biomarkers in RBD [90][91][92]; machine learning research in RBD [93,94]; and animal models of RBD [95][96][97][98]. In conclusion, RBD is situated at an important and ever-expanding crossroads of clinical (sleep) medicine, neurology, and neuroscience.…”

Section: Discussionmentioning

confidence: 99%

Update on Rapid-Eye-Movement Sleep Behavior Disorder (RBD): Focus on Its Strong Association with α-Synucleinopathies

Schenck

2023

CTN

View full text Add to dashboard Cite

REM sleep behavior disorder (RBD) is a parasomnia in which the customary generalized skeletal muscle atonia of REM sleep, “REM-atonia”, is compromised, allowing for the injurious acting-out of dreams. RBD can be idiopathic/isolated (iRBD) or symptomatic of neurological disorders, and can be triggered by most antidepressants. RBD mainly affects middle-aged and older adults, and is strongly linked with alpha-synucleinopathies, mainly Parkinson’s disease (PD) and dementia with Lewy bodies (DLB). iRBD is now known to be the earliest and strongest predictor of future PD/DLB, which has stimulated a major international clinical and basic science research effort to enroll iRBD patients for upcoming neuroprotective/disease-modifying trials and to identify the most promising interventions to test in these cohorts. This review will provide the latest pertinent information on the rapidly expanding field of RBD. The methods included a PubMed literature search that included PubCrawlers, which utilizes the NCBI (National Center for Biotechnology Information) E-utils tools for publication retrieval, using the keywords “REM sleep behavior disorder” and “RBD”. The results yielded the latest updates on iRBD as prodromal PD/DLB, with the most promising biomarkers for phenoconversion provided, along with a presentation of three clinical research consortiums that are systematically gathering patients in preparation for enrollment in upcoming clinical trials: (i) The International RBD Study Group; (ii) The North American Prodromal Synucleinopathy (NAPS and NAPS2) Consortium; and (iii) The FARPRESTO Italian multicenter RBD research consortium. In addition, updates on the Parasomnia Overlap Disorder (RBD + NREM parasomnia) and on narcolepsy-RBD are provided, along with new epidemiologic data, the latest RBD management guidelines, and updates on animal models of RBD. Emerging areas of critical RBD research are also highlighted. In conclusion, RBD is a notable example of clinical and translational neuroscience research.

show abstract

Section: Discussionmentioning

confidence: 99%

Update on Rapid-Eye-Movement Sleep Behavior Disorder (RBD): Focus on Its Strong Association with α-Synucleinopathies

Schenck

2023

CTN

View full text Add to dashboard Cite

show abstract

Automatic and Machine Learning Methods for Detection and Characterization of REM Sleep Behavior Disorder

Cesari,

Rechichi

2024

Springer Optimization and Its Applications

View full text Add to dashboard Cite

Refining sleep staging accuracy: transfer learning coupled with scorability models

Ganglberger,

Nasiri,

Sun

et al. 2024

Sleep

View full text Add to dashboard Cite

Study Objectives This study aimed to (1) improve sleep staging accuracy through transfer learning (TL), to achieve or exceed human inter-expert agreement and (2) introduce a scorability model to assess the quality and trustworthiness of automated sleep staging. Methods A deep neural network (base model) was trained on a large multi-site polysomnography (PSG) dataset from the United States. TL was used to calibrate the model to a reduced montage and limited samples from the Korean Genome and Epidemiology Study (KoGES) dataset. Model performance was compared to inter-expert reliability among three human experts. A scorability assessment was developed to predict the agreement between the model and human experts. Results Initial sleep staging by the base model showed lower agreement with experts (κ = 0.55) compared to the inter-expert agreement (κ = 0.62). Calibration with 324 randomly sampled training cases matched expert agreement levels. Further targeted sampling improved performance, with models exceeding inter-expert agreement (κ = 0.70). The scorability assessment, combining biosignal quality and model confidence features, predicted model-expert agreement moderately well (R² = 0.42). Recordings with higher scorability scores demonstrated greater model-expert agreement than inter-expert agreement. Even with lower scorability scores, model performance was comparable to inter-expert agreement. Conclusions Fine-tuning a pretrained neural network through targeted TL significantly enhances sleep staging performance for an atypical montage, achieving and surpassing human expert agreement levels. The introduction of a scorability assessment provides a robust measure of reliability, ensuring quality control and enhancing the practical application of the system before deployment. This approach marks an important advancement in automated sleep analysis, demonstrating the potential for AI to exceed human performance in clinical settings.

show abstract

Spatiotemporal characteristics of cortical activities of REM sleep behavior disorder revealed by explainable machine learning using 3D convolutional neural network

Cited by 6 publications

References 63 publications

Update on Rapid-Eye-Movement Sleep Behavior Disorder (RBD): Focus on Its Strong Association with α-Synucleinopathies

Update on Rapid-Eye-Movement Sleep Behavior Disorder (RBD): Focus on Its Strong Association with α-Synucleinopathies

Automatic and Machine Learning Methods for Detection and Characterization of REM Sleep Behavior Disorder

Refining sleep staging accuracy: transfer learning coupled with scorability models

Contact Info

Product

Resources

About