用任意传感器输入进行五级睡眠分期的深度生成模型
IEEE journal of biomedical and health informatics
|April 28, 2025
概括
我们开发了一种灵活的深度学习模型,用于使用各种传感器数据自动评分睡眠阶段. 这种先进的方法实现了高精度,即使在非传统或有限的传感器输入,提高睡眠分析可靠性.
科学领域:
- 计算神经科学是一种计算神经科学.
- 机器学习用于医疗保健
- 睡眠的药物 睡眠的药物
背景情况:
- 目前的睡眠评分依赖于电脑图 (EEG),电眼图 (EOG) 和电肌图 (EMG) 信号.
- 多睡眠学包括许多其他信号 (例如,心肺呼吸系统),这些信号在睡眠分期中未得到充分利用.
- 利用多样化的信号可以提高可靠性,对信号损失的弹性,并使长期的,非侵入性的记录成为可能.
研究的目的:
- 开发一种深度生成模型,用于自动睡眠分阶段,使用多种传感器模式的灵活组合.
- 通过利用新的贝叶斯因数分解,在任意传感器集上实现零射击推理.
- 引入一种新的可解释度指标,用于评估传感器对分类性能的贡献.
主要方法:
- 开发了一种基于分数的扩散模型,该模型是根据1947年专家标记的36个不同信号的夜间多睡眠记录进行训练的.
- 在不同的传感器组合中采用了新的贝叶斯分数函数的分数分解,用于在不同传感器组合中进行零射击推理.
- 提出并验证了与分类性能相关的基于信息获取的可解释性指标.
主要成果:
- 该模型的性能与单通道EEG的多睡眠学评价者间协议极限相提并论 (5类准确率为85.6%,科恩的卡帕为0.791).
- 通过非传统的传感器集,证明了灵活性,使用手指光电脉冲扫描,鼻流和胸部运动,达到79.0%的精度 (kappa 0.697).
- 展现了与骨和cleidomastoidEMG (71.0%准确率,kappa0.575) 的适应性,以及能够在后期纳入新的传感器的能力.
结论:
- 开发的深度生成模型为各种传感器配置的自动睡眠分阶段提供了灵活而强大的方法.
- 该模型实现了与黄金标准相比较的高性能,并且在有限或非常规的传感器输入下保持了准确性.
- 拟议的可解释性度量和后期传感器添加能力增强了该模型在睡眠研究中的实际实用性和适应性.
相关概念视频
01:22Stages of Sleep
150
Sleep progresses through distinct stages, each characterized by specific brain wave patterns and physiological responses ranging from wakefulness to stages of non-rapid eye movement, known as non-REM, to rapid eye movement, referred to as REM. Understanding these stages helps in recognizing how sleep supports various bodily and cognitive functions.
Before sleep begins, in wakefulness, the brain exhibits primarily beta waves, which are high in frequency and low in amplitude, indicating alertness...
Before sleep begins, in wakefulness, the brain exhibits primarily beta waves, which are high in frequency and low in amplitude, indicating alertness...
150
01:24Sleep-Wake Cycles
1.1K
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:
1.1K
01:19Management of Insomnia
185
The sleep cycle, an integral part of human health, consists of several stages with distinct characteristics and functions. It begins with a transition from wakefulness to sleep, known as the light sleep phase, followed by the restorative deep sleep phase, essential for physical recovery and growth. The cycle concludes with the Rapid Eye Movement (REM) phase, characterized by high brain activity and vivid dreaming. Insomnia, a prevalent sleep disorder, involves difficulty falling asleep, staying...
185
01:07Narcolepsy
82
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.
82
01:11Understanding Sleep
198
Sleep, an essential biological state, involves significant reductions in physical activity, sensory awareness, and interaction with the environment. This complex physiological process is primarily regulated by specific brain regions, notably the hypothalamus and pons, which govern the sleep-wake cycle or circadian rhythm.
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
198