A personalized semi-automatic sleep spindle detection (PSASD) framework
MohammadMehdi Kafashan1, Gaurang Gupte2, Paul Kang2
1Department of Anesthesiology, Washington University School of Medicine in St. Louis, St. Louis, MO, USA; Center on Biological Rhythms and Sleep, Washington University in St. Louis, St. Louis, MO, USA.
Journal of Neuroscience Methods
|February 1, 2024
Summary
A new Personalized Semi-Automatic Sleep Spindle Detection (PSASD) framework improves sleep spindle detection in electroencephalogram (EEG) data. This hybrid approach combines automated algorithms with human expertise for more accurate results in various populations.
Area of Science:
- Neuroscience
- Computational Biology
- Biomedical Engineering
Background:
- Sleep spindles are crucial EEG patterns for development, learning, and neurological disorders.
- Manual scoring of sleep spindles is time-consuming and prone to errors.
- Automated algorithms face challenges in accurately detecting sleep spindles.
Purpose of the Study:
- To develop a Personalized Semi-Automatic Sleep Spindle Detection (PSASD) framework.
- To integrate automated detection with human expertise for improved accuracy.
- To optimize sleep spindle detection in electroencephalogram (EEG) data.
Main Methods:
- Developed a PSASD framework utilizing a generative model for EEG sleep spindles.
- Implemented a graphical user interface (GUI) for manual scoring and automated verification.
- Employed a grid search approach for parameter optimization to balance precision and recall.
Main Results:
- PSASD demonstrated superior F1-scores compared to DETOKS and YASA on benchmark datasets.
- Outperformed four other widely used sleep spindle detectors in F1-score.
- Found that four 30-second epochs are sufficient for model parameter fine-tuning.
Conclusions:
- PSASD enhances the detection of sleep spindles in EEG data.
- The framework is effective across both younger healthy and older adult patient populations.
- PSASD offers a robust solution for accurate sleep spindle identification.
Related Concept Videos
01:24Sleep-Wake Cycles
1.3K
Sleep is an essential physiological process vital to maintaining overall well-being. The reticular activating system (RAS), a network of neurons in the brainstem, regulates wakefulness and sleep. While it may seem passive, sleep consists of distinct cycles, each with its unique characteristics and functions. Two key sleep phases are non-rapid eye movement (NREM) and rapid eye movement (REM).
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
1.3K
01:15REM Sleep Behavior Disorder
187
REM Sleep Behavior Disorder (RBD) is a sleep disorder characterized by the absence of muscle paralysis that normally occurs during the REM phase of sleep. This absence allows individuals to physically act out their dreams, which are often vivid and disturbing. Common behaviors exhibited during episodes include kicking, punching, and yelling. These actions can be dangerous, potentially leading to injuries for the person with RBD or their bed partner.
RBD is significantly associated with...
RBD is significantly associated with...
187
01:07Narcolepsy
103
Narcolepsy is a chronic sleep disorder characterized by pervasive, uncontrolled sleepiness and other sleep disturbances. One of its hallmark symptoms is an abrupt transition to REM sleep upon falling asleep, which causes symptoms typically associated with this phase to occur unexpectedly during wakefulness. These include the following symptoms, which typically last from a minute or two to half an hour.
103