相关实验视频
Updated: Jan 13, 2026

Multi-Modal Home Sleep Monitoring in Older Adults
Published on: January 26, 2019
一个用于疾病预测的多式睡眠基础模型.
Rahul Thapa1,2, Magnus Ruud Kjaer3,4,5, Bryan He2
1Department of Biomedical Data Science, Stanford University, Stanford, CA, USA.
一个新的基础模型,SleepFM,分析睡眠数据,从一晚的睡眠中预测超过130种疾病,包括死亡率和痴呆症. 这促进了对睡眠在健康和疾病预测中的作用的理解.
科学领域:
- 生物医学信息学 生物医学信息学
- 睡眠医学 睡眠医学
- 人工智能的人工智能
背景情况:
- 睡眠对健康至关重要,但它与疾病的联系是复杂的,多睡眠学 (PSG) 数据未得到充分利用.
- 现有的PSG分析方法在标准化,通用化和多式联运数据集成方面面临挑战.
研究的目的:
- 开发一种多式睡眠基础模型 (SleepFM),以克服PSG分析的局限性.
- 通过睡眠数据准确预测未来的疾病风险.
主要方法:
- 开发了使用多式联络PSG数据的新型对比学习方法的SleepFM.
- 训练了超过585,000小时的PSG录音,来自65,000名参与者.
- 利用潜伏睡眠表示来预测疾病和转移学习.
主要成果:
- 睡眠FM准确预测了130种疾病 (C指数≥0.75),包括死亡率,痴呆,心肌梗塞和慢性病.
- 在一个独立的数据集上表现出强大的转移学习.
- 通过专门的睡眠分阶段和睡眠呼吸暂停分类模型实现了竞争性表现.
结论:
- 基础模型可以有效地从多式联络睡眠记录中学习.
- 睡眠FM 能够实现可扩展,标签高效的睡眠分析和疾病预测.
- 这种方法提高了我们对睡眠对身体和精神健康的影响的理解.
更多相关视频
06:23A Chronic Sleep Fragmentation Model using Vibrating Orbital Rotor to Induce Cognitive Deficit and Anxiety-Like Behavior in Young Wild-Type Mice
Published on: September 22, 2020
14:27Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
相关概念视频
Substance Use Disorders Affecting Sleep
Understanding the concepts of physical dependence,...
Understanding Sleep
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...
REM Sleep Behavior Disorder
RBD is significantly associated with...
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Narcolepsy
Insufficient Sleep and Sleep Deprivation
Sleep deprivation is a more severe form of sleep loss...