使用基于机器学习的集群分析识别COPD的睡眠表型
Javad Razjouyan1, Nicola A Hanania2, Sara Nowakowski1
1VA's Health Services Research and Development Service (HSR&D), Center for Innovations in Quality, Effectiveness, and Safety, Michael E. DeBakey VA Medical Center, Houston, TX, 77030, USA; Big Data Scientist Training Enhancement Program, VA Office of Research and Development, Washington, DC, 20420, USA; VA Quality Scholars Coordinating Center, IQuESt, Michael E. DeBakey VA Medical Center, Houston, TX, 77030, USA; Section of Pulmonary and Critical Care Medicine, Department of Medicine, Baylor College of Medicine, Houston, TX, 77030, USA.
使用睡眠数据确定了五个慢性阻塞性肺病 (COPD) 患者群. 总睡眠时间和睡眠效率显著影响COPD患者的死亡风险.
科学领域:
- 肺部医学 肺部医学
- 睡眠医学 睡眠医学
- 数据科学数据科学数据科学
背景情况:
- 睡眠障碍显著影响生活质量,并预测慢性阻塞性肺病 (COPD) 患者的不良结果.
- 客观的睡眠参数对于了解COPD疾病进展和患者分层至关重要.
研究的目的:
- 在使用客观睡眠参数的COPD患者中识别不同的表型集群.
- 评估这些集群与全因死亡率之间的关联,以改善风险分层.
主要方法:
- 长度观察队列研究利用全国退伍军人卫生管理局的数据.
- 无监督的机器学习 (K-means集群) 应用于9992名COPD患者的多睡眠学数据.
- 考克斯回归分析和卡普兰-梅尔估计用于评估死亡率关联.
主要成果:
- 根据年龄,并发症负担和睡眠参数确定了五个不同的患者群.
- 死亡率在各个集群中差异很大,从9.4%到42%整体.
- 总睡眠时间和睡眠效率在特定集群中与死亡率有显著的关联.
结论:
- 客观的睡眠参数对于表型特征和COPD死亡风险评估至关重要.
- 鉴定到的集群为COPD患者基于睡眠特征进行分层提供了一种新的方法.
- 对睡眠障碍呼吸干预措施的进一步研究可能会改善高风险COPD患者的治疗结果.
更多相关视频
相关概念视频
Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History
Chronic Obstructive Pulmonary Disease-I: Introduction
COPD: Management Using Bronchodilators and Corticosteroids
Chronic Obstructive Pulmonary Disease
Smoking is a primary risk factor for COPD, with over 80% of patients having a history of it. Patients typically experience progressive dyspnea or labored breathing, frequent coughing, and recurrent pulmonary infections. Many eventually succumb to respiratory failure, characterized by...
Sleep Apnea
The condition is more prevalent among...
COPD: Pathogenesis and Clinical Features
The primary cause for the onset of COPD is cigarette smoking and exposure to air pollution. These hazardous factors initiate a chain reaction within the lungs, resulting in chronic inflammation, damage to the airways, and a...


