基于多睡眠记录的睡眠呼吸暂停事件识别:一个大规模的多通道机器学习方法
Nicolo La Porta1,2,3, Stefano Scafa3,4,5, Michela Papandrea2
1Faculty of InformaticsUniversità della Svizzera Italiana (USI) 6900 Lugano Switzerland.
IEEE open journal of engineering in medicine and biology
|December 19, 2024
概括
这项研究引入了一个人工智能模型,用于自动检测睡眠呼吸暂停事件,比手动分析提高准确性和效率. 机器学习方法为诊断睡眠呼吸暂停-睡眠暂停综合征提供了更容易获得和更可靠的方法.
科学领域:
- 医疗信息学 医疗信息学
- 人工智能在医学中的应用
- 睡眠医学 睡眠医学
背景情况:
- 对呼吸暂停事件的手动多睡眠学解释是耗时的,昂贵的,容易出现错误的.
- 目前的睡眠呼吸暂停-呼吸暂停综合征的诊断协议需要专门的设施,导致长时间的等待时间.
- 人工智能 (AI) 为提高睡眠呼吸暂停诊断的准确性和效率提供了一个有希望的解决方案.
研究的目的:
- 开发和验证基于机器学习的方法,用于自动检测呼吸暂停事件.
- 使用人工智能改进睡眠呼吸暂停-睡眠暂停综合征的诊断过程.
- 建立一种更有效,更准确的方法来识别与睡眠相关的呼吸障碍.
主要方法:
- 利用了威斯康星睡眠队列 (WSC) 数据库,这是一个庞大而多样化的受试者数据集.
- 开发了一种机器学习模型,用于自动识别呼吸暂停事件.
- 评估模型在事件检测和分类不同类型的呼吸暂停的性能.
主要成果:
- 在自动检测呼吸暂停事件时,总体准确度为87.2±1.8%.
- 与同一个数据集上的现有方法相比,证明了显著更高的准确性.
- 为了区分不同类型的呼吸暂停,获得了62.9±4.1%的整体准确度.
结论:
- 拟议的AI方法增强了睡眠呼吸暂停事件的识别,比最先进的方法提供了更好的性能.
- 经过验证的方法提供了一种简单和可解释的方式,可以通过信号的子集来识别睡眠呼吸暂停事件.
- 这种人工智能驱动的解决方案扩大了睡眠呼吸暂停诊断的可能性,潜在地提高了医疗保健的质量和可访问性.
相关概念视频
Narcolepsy
89
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.
89
Sleep-Wake Cycles
1.2K
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:
1.2K
Sleepwalking and Sleep Talking
119
Somnambulism, commonly known as sleepwalking, involves individuals engaging in activities ranging from simple walking to more complex behaviors such as driving. Sleepwalking typically occurs during the slow-wave sleep stages 3 and 4 early in the night when the person is not dreaming, contradicting the myth that sleepwalkers are acting out their dreams.
Factors that increase the likelihood of sleepwalking include sleep deprivation and alcohol consumption. Contrary to common beliefs, it is safe...
Factors that increase the likelihood of sleepwalking include sleep deprivation and alcohol consumption. Contrary to common beliefs, it is safe...
119


