%0期刊文章%@ 1438- 8871% I JMIR出版物%V 20卡塔尔世界杯8强波胆分析% N 9% P e263% T改善慢性阻塞性肺疾病住院风险预测:机器学习在远程监控数据中的应用，Peter Agakova,Anna Pinnock,Hilary Burton,Christopher David Sarran,Christophe Agakov,Felix McKinstry,Brian + Usher人口健康科学与信息学研究所，爱丁堡大学，9号生物区，小法国路9号，爱丁堡，EH16 4UX，英国，44 1316502378，brian.mckinstry@ed.ac.uk %K机器学习%K远程医疗%K慢性阻塞性肺疾病%D 2018 %7 21.9.2018 %9原始论文%J J医学互联网Res %G英文%X背景:症状和生理体征的远程监测已被建议作为早期发现慢性阻塞性肺疾病(COPD)加重的一种手段，以便及时治疗。然而，识别病情加重的算法会导致频繁的假阳性结果和增加工作量。当机器学习应用于预测建模时，可以确定有助于提高预测质量的风险因素模式。目的:我们的目标是:(1)确定应用于远程监测数据集的机器学习技术是否改善了医院入院和开始使用皮质类固醇的决定的预测，(2)确定天气数据的添加是否进一步改善了这种预测。方法:我们采用COPD远程监测试点和大型随机对照试验的日常症状、生理指标和用药数据，以及基线人口统计学、COPD严重程度、生活质量和入院率。我们把来自英国气象部门的天气数据联系起来。我们使用时间序列的特征选择和提取技术，从症状、药物和生理测量中构建了多达153种预测模式(特征)。我们使用得到的变量构建适合训练患者集的预测模型，并将其与常见的症状计数算法进行比较。 Results: We had a mean 363 days of telemonitoring data from 135 patients. The two most practical traditional score-counting algorithms, restricted to cases with complete data, resulted in area under the receiver operating characteristic curve (AUC) estimates of 0.60 (95% CI 0.51-0.69) and 0.58 (95% CI 0.50-0.67) for predicting admissions based on a single day’s readings. However, in a real-world scenario allowing for missing data, with greater numbers of patient daily data and hospitalizations (N=57,150, N+=55, respectively), the performance of all the traditional algorithms fell, including those based on 2 days’ data. One of the most frequently used algorithms performed no better than chance. All considered machine learning models demonstrated significant improvements; the best machine learning algorithm based on 57,150 episodes resulted in an aggregated AUC of 0.74 (95% CI 0.67-0.80). Adding weather data measurements did not improve the predictive performance of the best model (AUC 0.74, 95% CI 0.69-0.79). To achieve an 80% true-positive rate (sensitivity), the traditional algorithms were associated with an 80% false-positive rate: our algorithm halved this rate to approximately 40% (specificity approximately 60%). The machine learning algorithm was moderately superior to the best symptom-counting algorithm (AUC 0.77, 95% CI 0.74-0.79 vs AUC 0.66, 95% CI 0.63-0.68) at predicting the need for corticosteroids. Conclusions: Early detection and management of COPD remains an important goal given its huge personal and economic costs. Machine learning approaches, which can be tailored to an individual’s baseline profile and can learn from experience of the individual patient, are superior to existing predictive algorithms and show promise in achieving this goal. Trial Registration: International Standard Randomized Controlled Trial Number ISRCTN96634935; http://www.isrctn.com/ISRCTN96634935 (Archived by WebCite at http://www.webcitation.org/722YkuhAz) %M 30249589 %R 10.2196/jmir.9227 %U //www.mybigtv.com/2018/9/e263/ %U https://doi.org/10.2196/jmir.9227 %U http://www.ncbi.nlm.nih.gov/pubmed/30249589