使用粗粒度标签监测睡眠呼吸暂停严重性的弱监督深度学习
Xin Zan1, Di Wang2, Changyue Song3
1Department of Industrial and Systems Engineering, The University of Iowa, IA, USA.
概括
这项研究引入了一个弱监督的深度学习模型来估计睡眠呼吸暂停的严重程度. 这种方法降低了标签成本,为睡眠呼吸暂停患者提供了更广泛的诊断.
科学领域:
- 生物医学工程
- 医学的人工智能
- 睡眠医学
背景情况:
- 睡眠呼吸暂停的诊断依赖于手动注释生理信号,这是耗时和昂贵的.
- 目前用于无呼吸检测的机器学习方法需要大量精细标记的数据,从而限制了其临床应用.
- 不被诊断的睡眠呼吸暂停影响了大量患者,强调需要更容易获得的诊断工具.
研究的目的:
- 开发一个弱监督的深度学习框架,以仅使用粗粒度标签来估计细粒度睡眠呼吸暂停的严重程度.
- 将临床知识纳入深度学习模型,以提高呼吸暂停严重程度的准确性.
- 减少对睡眠呼吸暂停诊断的昂贵手动标签的依赖.
主要方法:
- 一个新的知识增强的双颗粒度一致性损失旨在改善细粒度呼吸暂停的严重性学习.
- 临床知识是使用顺序对齐函数进行数学编码以校准估计的准确性.
- 该框架使用粗粒度标签 (呼吸暂停存在) 来估计细粒度的严重程度.
主要成果:
- 拟议的方法可以准确地估计细粒度睡眠呼吸暂停的严重程度.
- 与传统的监督方法相比,标签成本大大降低.
- 该模型在高时间分辨率下监测呼吸暂停的严重程度方面表现出卓越的性能.
结论:
- 低监督的深度学习,加上临床知识,为睡眠呼吸暂停的严重程度估计提供了有效的解决方案.
- 这种方法可以显著降低诊断成本,并扩大睡眠呼吸暂停监测的机会.
- 开发的框架对实验室和家庭的睡眠呼吸暂停诊断具有前景.
相关概念视频
Sleep Apnea
220
Sleep apnea is a condition where breathing stops intermittently during sleep, often leading to significant health issues. Each episode can last from 10 to 20 seconds or more and is frequently accompanied by a brief arousal from sleep. This disturbance, largely unnoticed by the individual, can lead to severe daytime fatigue. Commonly, individuals seek help after being informed by their partners about loud snoring and noticeable breathing pauses during sleep.
The condition is more prevalent among...
The condition is more prevalent among...
220
Understanding Sleep
502
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...
502
Neural Control of Respiration
2.9K
The neural regulation of respiration is a meticulously coordinated process primarily controlled by the respiratory centers located within the brainstem. These centers, composed of specialized neurons, transmit nerve impulses that control the contraction and relaxation of our respiratory muscles.
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
2.9K
Sleep-Wake Cycles
1.6K
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:
1.6K


