基于无创参数辨识急性呼吸窘迫综合征患者疾病严重程度的算法研究
|
摘要
急性呼吸窘迫综合征(ARDS)是一种严重威胁人类生命健康的疾病,具有起病急、病死率高等特点。目前这种疾病的主要诊断和疾病严重程度分级标准依赖于血气分析结果,从而计算患者的氧合指数(PaO_2/FiO_2,P/F),但是血气分析是有创操作,且不能连续监测病情的发展。针对以上问题,我们提出了一种新的ARDS疾病严重程度的辨识算法。基于患者的多种无创生理参数,结合特征选择技术,对多种生理参数进行重要性排序。利用交叉验证技术评估辨识性能,比较不同特征子集下,使用神经网络、逻辑回归、AdaBoost、Bagging四种监督学习算法的分类结果。通过不同特征子集下不同算法的敏感性、特异性、准确率、曲线下面积(AUC)来综合选择最优的特征子集和分类算法。我们利用四种监督学习算法,对ARDS严重程度进行区分(P/F≤300)。根据AUC来评估算法性能,AdaBoost在使用20个特征时,AUC=0.832 1,准确率为74.82%,取得了最优的AUC。根据特征个数来评估算法性能,Bagging在使用2个特征时,AUC=0.819 4,准确率为73.01%。该方法相较于传统方法有较大的优势,能够连续监测ARDS患者的病情发展,为医务人员提供辅助诊断建议。
Acute respiratory distress syndrome(ARDS) is a serious threat to human life and health disease,with acute onset and high mortality. The current diagnosis of the disease depends on blood gas analysis results, while calculating the oxygenation index. However, blood gas analysis is an invasive operation, and can't continuously monitor the development of the disease. In response to the above problems, in this study, we proposed a new algorithm for identifying the severity of ARDS disease. Based on a variety of non-invasive physiological parameters of patients,combined with feature selection techniques, this paper sorts the importance of various physiological parameters. The cross-validation technique was used to evaluate the identification performance. The classification results of four supervised learning algorithms using neural network, logistic regression, AdaBoost and Bagging were compared under different feature subsets. The optimal feature subset and classification algorithm are comprehensively selected by the sensitivity, specificity, accuracy and area under curve(AUC) of different algorithms under different feature subsets. We use four supervised learning algorithms to distinguish the severity of ARDS(P/F ≤ 300). The performance of the algorithm is evaluated according to AUC. When AdaBoost uses 20 features, AUC = 0.832 1, the accuracy is 74.82%, and the optimal AUC is obtained. The performance of the algorithm is evaluated according to the number of features. When using 2 features, Bagging has AUC = 0.819 4 and the accuracy is 73.01%. Compared with traditional methods, this method has the advantage of continuously monitoring the development of patients with ARDS and providing medical staff with auxiliary diagnosis suggestions.
Acute respiratory distress syndrome(ARDS) is a serious threat to human life and health disease,with acute onset and high mortality. The current diagnosis of the disease depends on blood gas analysis results, while calculating the oxygenation index. However, blood gas analysis is an invasive operation, and can't continuously monitor the development of the disease. In response to the above problems, in this study, we proposed a new algorithm for identifying the severity of ARDS disease. Based on a variety of non-invasive physiological parameters of patients,combined with feature selection techniques, this paper sorts the importance of various physiological parameters. The cross-validation technique was used to evaluate the identification performance. The classification results of four supervised learning algorithms using neural network, logistic regression, AdaBoost and Bagging were compared under different feature subsets. The optimal feature subset and classification algorithm are comprehensively selected by the sensitivity, specificity, accuracy and area under curve(AUC) of different algorithms under different feature subsets. We use four supervised learning algorithms to distinguish the severity of ARDS(P/F ≤ 300). The performance of the algorithm is evaluated according to AUC. When AdaBoost uses 20 features, AUC = 0.832 1, the accuracy is 74.82%, and the optimal AUC is obtained. The performance of the algorithm is evaluated according to the number of features. When using 2 features, Bagging has AUC = 0.819 4 and the accuracy is 73.01%. Compared with traditional methods, this method has the advantage of continuously monitoring the development of patients with ARDS and providing medical staff with auxiliary diagnosis suggestions.
引文
1葛均波,徐永健.内科学.第8版.北京:人民卫生出版社,2013.
2 Bellani G,Laffey J G,Pham T,et al. Epidemiology,patterns of care:and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries.JAMA,2016,315(8):788-800.
3 Riviello E D,Kiviri W,Twagirumugabe T,et al. Hospital incidenceand outcomes of the acute respiratory distress syndrome using the Kigali modification of the Berlin definition.Am J Respir Crit Care Med,2016,193(1):52-59.
4 Maybauer M O,Maybauer D M, Herndon D N.Incidence and outcomes of acute lung injury.N Engl J Med,2006,354(4):416-417.
5 Ranieri V M, Rubenfeld G D, Thompson B T, et al. Acute respiratory distress syndrome the Berlin definition.JAMA,2012,307(23):2526-2533.
6 Luo L,Shaver C M,Zhao Z G,et al. Clinical predictors of hospital mortality differ between direct and indirect ARDS. Chest,2016,151(4):755-763.
7 Garland A.Arterial lines in the ICU:a call for rigorous controlled trials.Chest,2014,146(5):1155-1158.
8向有喜,彭菲,彭再梅.急性呼吸窘迫综合征的诊治现状与展望.中华急诊医学杂志,2017,26(3):255-259.
9 Bilan N,Dastranji A,Ghalehgolab Behbahani A.Comparison of the SpO2/FiO2 ratio and the Pa02/FiO2 ratio in patients with acute lung injury or acute respiratory distress syndrome.Chest,2007,132(2):410-417.
10滕丽华,谢志毅,徐军,等.以SPO_2替代PaO_2评估急性呼吸窘迫综合征机械通气患者脱机指征的可行性分析.临床误诊误治,2017(7):62-65.
11 Brown S M,Grissom C K,Moss M,et al. Non-linear imputation of Pa02/FI02,from SpO2/FIO2,among patients with acute respiratory distress syndrome.Chest,2016,150(2):307-313.
12 Ahmed A,Kojicic M,Herasevich V,et al. Early identification of patients with or at risk of acute lung injury.Netherlands Journal of Medicine,2009,67(9):268-271.
13 Johnson A E W,Pollard T J,Shen Lu,et al.MIMIC-Ⅲ,a freely accessible critical care database.Scientific Data,2016,3:160035.
14 Scheuren F.Multiple imputation. American Statistician,2005,59(4):315-319.
15 Alonso-Atienza F, Morgado E, Fernandez-Martinez L, et al.Detection of life-threatening arrhythmias using feature selection and support vector machines. IEEE Trans Biomed Eng, 2014,61(3):832-840.
16 Benesty J,Chen J,Huang Y,et al. Pearson correlation coefficient.Noise Reduction in Speech Processing.Springer Berlin Heidelberg:2009:1-4.
2 Bellani G,Laffey J G,Pham T,et al. Epidemiology,patterns of care:and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries.JAMA,2016,315(8):788-800.
3 Riviello E D,Kiviri W,Twagirumugabe T,et al. Hospital incidenceand outcomes of the acute respiratory distress syndrome using the Kigali modification of the Berlin definition.Am J Respir Crit Care Med,2016,193(1):52-59.
4 Maybauer M O,Maybauer D M, Herndon D N.Incidence and outcomes of acute lung injury.N Engl J Med,2006,354(4):416-417.
5 Ranieri V M, Rubenfeld G D, Thompson B T, et al. Acute respiratory distress syndrome the Berlin definition.JAMA,2012,307(23):2526-2533.
6 Luo L,Shaver C M,Zhao Z G,et al. Clinical predictors of hospital mortality differ between direct and indirect ARDS. Chest,2016,151(4):755-763.
7 Garland A.Arterial lines in the ICU:a call for rigorous controlled trials.Chest,2014,146(5):1155-1158.
8向有喜,彭菲,彭再梅.急性呼吸窘迫综合征的诊治现状与展望.中华急诊医学杂志,2017,26(3):255-259.
9 Bilan N,Dastranji A,Ghalehgolab Behbahani A.Comparison of the SpO2/FiO2 ratio and the Pa02/FiO2 ratio in patients with acute lung injury or acute respiratory distress syndrome.Chest,2007,132(2):410-417.
10滕丽华,谢志毅,徐军,等.以SPO_2替代PaO_2评估急性呼吸窘迫综合征机械通气患者脱机指征的可行性分析.临床误诊误治,2017(7):62-65.
11 Brown S M,Grissom C K,Moss M,et al. Non-linear imputation of Pa02/FI02,from SpO2/FIO2,among patients with acute respiratory distress syndrome.Chest,2016,150(2):307-313.
12 Ahmed A,Kojicic M,Herasevich V,et al. Early identification of patients with or at risk of acute lung injury.Netherlands Journal of Medicine,2009,67(9):268-271.
13 Johnson A E W,Pollard T J,Shen Lu,et al.MIMIC-Ⅲ,a freely accessible critical care database.Scientific Data,2016,3:160035.
14 Scheuren F.Multiple imputation. American Statistician,2005,59(4):315-319.
15 Alonso-Atienza F, Morgado E, Fernandez-Martinez L, et al.Detection of life-threatening arrhythmias using feature selection and support vector machines. IEEE Trans Biomed Eng, 2014,61(3):832-840.
16 Benesty J,Chen J,Huang Y,et al. Pearson correlation coefficient.Noise Reduction in Speech Processing.Springer Berlin Heidelberg:2009:1-4.