基于规模的度测量和深度学习方法,用于分析COVID-19受试者在康复期间和之后心肺呼吸系统控制系统的动态特征
Madini O Alassafi1, Wajid Aziz2, Rayed AlGhamdi1
1Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia.
Computers in biology and medicine
|February 4, 2024
概括
这项研究表明,使用基于尺度的 (SBE) 和深度学习分析氧和度变化 (OSV) 信号可以区分COVID-19疾病和康复. 多尺度模糊 (MFE) 与辐射基函数网络 (RBFN) 在分类这些心肺呼吸信号方面取得了高准确性.
科学领域:
- 生理学 生理学 生理学
- 生物医学工程 生物医学工程
- 数据科学数据科学数据科学
背景情况:
- COVID-19 (冠状病毒疾病2019) 主要影响呼吸系统,但可能导致心肺呼吸系统并发症.
- 在COVID-19患者中评估心肺控制系统 (CRCS) 动态对于临床决策至关重要.
- 基于的复杂度测量提供了分析生理信号的新方法,例如氧和度变化 (OSV).
研究的目的:
- 使用基于尺度的 (SBE) 方法来描述COVID-19疾病和恢复期间OSV信号的动态复杂性.
- 应用机器学习 (ML) 和深度学习 (DL) 技术来根据SBE特征对OSV信号进行分类.
- 评估不同SBE措施和DL模型在检测COVID-19患者CRCS功能障碍方面的有效性.
主要方法:
- 采集了44名COVID-19患者在活跃感染期间和康复后两个月使用Beurer PO-80脉冲氧计收集的非侵入性OSV和脉冲率数据.
- 应用了SBE方法,包括多尺度 (MSE),多尺度顺序 (MPE) 和多尺度模糊 (MFE),以描述OSV信号复杂性.
- 利用深度学习模型,特别是辐射基函数网络 (RBFN) 和带动态延迟算法 (RBFNDDA) 的 RBFN,将 SBE 测量作为分类的输入特征.
主要成果:
- 基于规模的分析显示,与康复阶段相比,在活跃的COVID-19感染期间,OSV信号复杂性减少.
- 与RBFN结合的多尺度模糊 (MFE) 显示出优异的分类性能,达到0.84的灵敏度,0.70的特异性和0.77.7的曲线下面面积 (AUC).
- 该分类模型有效地区分了来自COVID-19疾病和康复期的OSV数据.
结论:
- 在COVID-19期间,SBE测量,特别是MFE,对于量化心肺呼吸系统动态变化是有效的.
- 将SBE措施与RBFN等深度学习模型的整合提供了一个强大的方法来分类与COVID-19相关的OSV信号.
- 这种方法有助于识别COVID-19患者的心肺控制系统功能障碍,并可以支持疾病和康复期间的临床评估.
更多相关视频
相关概念视频
01:29Assessment of Ventilation II: Respiratory Depth and Rhythm
1.5K
Respiratory Depth
Respiratory depth measures the volume of air inhaled or exhaled during a breath. It can vary from shallow to deep and typically remains consistent when a person is at rest or asleep. Occasionally, individuals will automatically inhale deeply, known as sighing, which inflates the lungs with more air than normal breathing.
To assess respiratory depth, observe the degree of chest excursion or movement:
Respiratory depth measures the volume of air inhaled or exhaled during a breath. It can vary from shallow to deep and typically remains consistent when a person is at rest or asleep. Occasionally, individuals will automatically inhale deeply, known as sighing, which inflates the lungs with more air than normal breathing.
To assess respiratory depth, observe the degree of chest excursion or movement:
1.5K
01:30Alterations in Respiration II
866
There are numerous types of normal and abnormal respiration. Based on ventilatory movements, breathing patterns are classified as regular, deep, or shallow. Examples include Biot's breathing, Cheyne-Stokes respiration, Kussmaul's breathing, hyperventilation, and hypoventilation. Each pattern is clinically significant and aids in evaluating patients.
In Biot's breathing, the respiratory rate and depth are irregular, alternating between periods of deep gasping and apnea. Common causes...
In Biot's breathing, the respiratory rate and depth are irregular, alternating between periods of deep gasping and apnea. Common causes...
866