利用家庭远程医疗测量数据预测慢性阻塞性肺疾病患者的病情加重风险。
Predicting the risk of exacerbation in patients with chronic obstructive pulmonary disease using home telehealth measurement data.
作者信息
Mohktar Mas S, Redmond Stephen J, Antoniades Nick C, Rochford Peter D, Pretto Jeffrey J, Basilakis Jim, Lovell Nigel H, McDonald Christine F
机构信息
Graduate School of Biomedical Engineering, University of New South Wales, Sydney, NSW 2052, Australia; Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia.
Graduate School of Biomedical Engineering, University of New South Wales, Sydney, NSW 2052, Australia.
出版信息
Artif Intell Med. 2015 Jan;63(1):51-9. doi: 10.1016/j.artmed.2014.12.003. Epub 2014 Dec 18.
BACKGROUND
The use of telehealth technologies to remotely monitor patients suffering chronic diseases may enable preemptive treatment of worsening health conditions before a significant deterioration in the subject's health status occurs, requiring hospital admission.
OBJECTIVE
The objective of this study was to develop and validate a classification algorithm for the early identification of patients, with a background of chronic obstructive pulmonary disease (COPD), who appear to be at high risk of an imminent exacerbation event. The algorithm attempts to predict the patient's condition one day in advance, based on a comparison of their current physiological measurements against the distribution of their measurements over the previous month.
METHOD
The proposed algorithm, which uses a classification and regression tree (CART), has been validated using telehealth measurement data recorded from patients with moderate/severe COPD living at home. The data were collected from February 2007 to January 2008, using a telehealth home monitoring unit.
RESULTS
The CART algorithm can classify home telehealth measurement data into either a 'low risk' or 'high risk' category with 71.8% accuracy, 80.4% specificity and 61.1% sensitivity. The algorithm was able to detect a 'high risk' condition one day prior to patients actually being observed as having a worsening in their COPD condition, as defined by symptom and medication records.
CONCLUSION
The CART analyses have shown that features extracted from three types of physiological measurements; forced expiratory volume in 1s (FEV1), arterial oxygen saturation (SPO2) and weight have the most predictive power in stratifying the patients condition. This CART algorithm for early detection could trigger the initiation of timely treatment, thereby potentially reducing exacerbation severity and recovery time and improving the patient's health. This study highlights the potential usefulness of automated analysis of home telehealth data in the early detection of exacerbation events among COPD patients.
背景
使用远程医疗技术对慢性病患者进行远程监测，可能会在患者健康状况显著恶化并需要住院治疗之前，对病情恶化进行预防性治疗。
目的
本研究的目的是开发并验证一种分类算法，用于早期识别有慢性阻塞性肺疾病（COPD）背景且似乎即将发生急性加重事件的高风险患者。该算法试图根据患者当前的生理测量值与前一个月测量值的分布进行比较，提前一天预测患者的病情。
方法
所提出的算法使用分类回归树（CART），已通过对在家中生活的中度/重度COPD患者记录的远程医疗测量数据进行了验证。这些数据是在2007年2月至2008年1月期间，使用远程医疗家庭监测设备收集的。
结果
CART算法可以将家庭远程医疗测量数据分为“低风险”或“高风险”类别，准确率为71.8%，特异性为80.4%，敏感性为61.1%。该算法能够在患者实际被观察到COPD病情恶化前一天检测到“高风险”状态，病情恶化由症状和用药记录定义。
结论
CART分析表明，从三种生理测量值中提取的特征；一秒用力呼气量（FEV1）、动脉血氧饱和度（SPO2）和体重在对患者病情分层方面具有最强的预测能力。这种用于早期检测的CART算法可以触发及时治疗的启动，从而有可能降低急性加重的严重程度和恢复时间，并改善患者的健康状况。本研究强调了家庭远程医疗数据自动分析在COPD患者急性加重事件早期检测中的潜在有用性。
Zotero 插件