摘要
心力衰竭是各种心脏疾病的严重阶段,其发病率高,死亡率高,已经成为全球范围内的重大公共卫生问题。而临床实践中,心力衰竭的确诊率和控制率很低,造成以上问题的原因之一就是缺乏有效的心力衰竭疾病评估方法。
本课题运用工程技术方法,并结合临床医学,建立了基于多生理参数的心力衰竭疾病评估模型,综合ACC/AHA分期和定量评分体系来评估心力衰竭。本课题主要完成了以下工作:
1)对临床数据进行分析,筛选出了与心力衰竭相关联的特征参数。
2)利用支持向量机算法对心力衰竭进行分级。
3)运用模糊多级分析方法对病情综合评分:首先利用聚类分析方法将生理参数划分为七个子类,并利用隶属函数获取生理参数的模糊隶属度,然后对各类生理参数的模糊隶属度加权求和产生一级指标值,最后计算一级指标的加权和并进行综合评分。其中,生理参数和一级指标的权重由判断矩阵、主成分分析等方法实现。
4)经上述工作建立的心衰评估模型可对心力衰竭进行分级和定量评分,将该模型应用于临床病例分析,验证模型效果。
研究结果表明,聚类分析得到的心功能、心结构、体液潴留、运动耐量、电生理、生化功能、神经活性等七个一级指标的生理意义和临床指示意义明确。应用模型对130-例样本进行心衰分级,正确率达到81.5%,ACC/AHA分期的完全健康/A分期、B分期和C分期的正确率分别为83.9%,82.9%和75.8%,并且模型鉴别出了20例临床错分的病例;对237例样本进行定量评分,得分值在ACC/AHA各分期间具有显著性差异,与ACC/AHA分期相关。
模型实现了对心衰的有效分级,且综合得分定量指示了心力衰竭的严重程度。模型的定量、客观特性,有助于减少临床中主观性导致的评估错误。本课题建立的模型为心力衰竭评估提供了一种新思路,具有良好的应用前景。
Heart failure is a serious stage of various heart diseases. Due to its high morbidity and mortality, heart failure has become a worldwide public health problem. However, the diagnostic rate and the control rate of heart failure in clinic are very low, which is mainly ascribed to the lack of effective assessment methods for heart failure.
By means of engineering technology and medical knowledge, a heart failure disease assessment model based on physiological parameters was established. This model is able to stratify heart failure into ACC/AHA stages and give comprehensive quantitative scores. The main work and achievements are summarized as follows:
1) Analyze clinical data, and obtain heart failure characteristic parameters.
2) Stratify heart failure with the aid of support vector machine algorithm (SVM).
3) Utilize fuzzy multi-level analysis to assess heart failure:firstly, employ cluster analysis to classify physiological parameters into seven catalogs, apply membership function to obtain fuzzy membership of physiological parameters, then produce grade indexes through a weighted sum of fuzzy membership, finally calculate the weighted sum of the grade indexes to gain a comprehensive score. The involved physiological parameters and a target weights are achieved by Matrix methods and principal component analysis.
4) Use the established model to classify and score heart failure, apply and verify the model in clinical cases.
The results show that, the cataloged seven indexes, i.e. cardiac function, cardiac structure, fluid overload, exercise tolerance, electronic physiology parameters, biochemistry parameters and neural activity have distinguished physiological and clinical meanings. The total stratification accuracy in 108 cases is 81.5%, and the accuracies for Health/A stage, B and C stage are 83.9%,82.9% and 75.8%, respectively. Furthermore, the model successfully detected 20 cases, which are misclassified in clinic. Tested in 237 cases, the given scores for the three stages of ACC/ACH are significantly different.
In conclusion, the developed model achieved effective stratification in heart failure and the scores indicate the severity of heart failure properly. Since the model is quantitative and objective, it helps reduce the subjective errors in clinical assessment. The model provides a new approach for the valuation of heart failure and has a great prospect in clinical application.
引文
[1]钱俊峰,”我国慢性心力衰竭流行病学和治疗现状,”中国临床医学,vol.16,pp.300-303,2009.
[2]http://www.cardioupdate.com.cn/doc/icd=102.html.
[3]S. Stewart, K. MacIntyre, S. Capewell,J. J. V. McMurray, "Heart failure and the aging population:an increasing burden in the 21st century," Heart, vol.89, pp.49-53,2003.
[4]徐国辰,“慢性心力衰竭基础与临床进展,”心血管病学进展,vol.26,pp.109-103,2005.
[5]R. A. Clark, S. McLennan, A. Dawson, D. Wilkinson,S. Stewart, "Uncovering a hidden epidemic:a study of the current burden of heart failure in australia," Heart, Lung and Circulation, vol.13, pp.266-273,2004.
[6]K. Dickstein, A. Cohen-Solal, G. Filippatos, J. J. V. McMurray, P. Ponikowski, P. A. Poole-Wilson, et al., "ESC guidelines for the diagnosis and treatment of acute and chronic heart failure 2008," European Heart Journal, vol.29, pp. 2388-2442,2008.
[7]R. S. Vasan, L. M. Sullivan, R. Roubenoff, C. A. Dinarello, T. Harris, E. J. Benjamin, et al., "Inflammatory markers and risk of heart failure in elderly subjects without prior myocardial infarction:the framingham heart study," Circulation, vol.107, pp.1486-1491,2003.
[8]K. K. L. Ho, G. B. Moody, C.-K. Peng, J. E. Mietus, M. G. Larson, D. Levy, et al., "Predicting survival in heart failure case and control subjects by use of fully automated methods for deriving nonlinear and conventional indices of heart rate dynamics," Circulation, vol.96, pp.842-848,1997.
[9]http://www.china-xnxgb.com/xnxgb/jibingzhuanti/01/0101.htm.
[10]S. A. Hunt, W. T. Abraham, M. H. Chin, A. M. Feldman, G. S. Francis, T. G Ganiats, et al., "ACC/AHA 2005 guideline update for the diagnosis and management of chronic heart failure in the adult:a report-of the american college of cardiology/american heart association task force on practice guidelines (writing committee to update the 2001 guidelines for the evaluation and management of heart failure):developed in collaboration with the american college of chest physicians and the international society for heart and lung transplantation:endorsed by the heart rhythm society," Circulation, vol. 112,pp.e154-235,2005.
[11]杜昕,“心力衰竭诊断与治疗的几个问题,”中华心血管病杂志,vol.31,pp.539-541,2003.
[12]A. Fuat, A. P. S. Hungin,J. J. Murphy, "Barriers to accurate diagnosis and effective management of heart failure in primary care:qualitative study," BMJ, vol.326, pp.196-201,2003.
[13]R. A. Miller, "Computer-assisted diagnostic decision support:history, challenges, and possible paths forward," Advances in Health Sciences Education, vol.14, pp.89-106,2009.
[14]W. R. M. Dassen, A. P. M. Gorgels, A. Berendsen, W. A. Dijk, P. A. de Clercq, A. Hasman, et al., "Guideline assessment and implementation in congestive heart failure," Computers in Cardiology, pp.331-334,2003.
[15]G. P. Purcell, "What makes a good clinical decision support system," BMJ, vol. 330, pp.740-741,2005.
[16]J. Fox, V. Patkar, I. Chronakis,R. Begent, "From practice guidelines to clinical decision support:closing the loop," J R Soc Med, vol.102, pp.464-73,2009.
[17]K. Kawamoto, C. A. Houlihan, E. A. Balas,D. F. Lobach, "Improving clinical practice using clinical decision support systems:a systematic review of trials to identify features critical to success," BMJ:British Medical Journal, vol.330, pp.765-768,2005.
[18]E. H. Shortliffe, R. Davis, S. G. Axline, B. G. Buchanan, C. C. Green,S. N. Cohen, "Computer-based consultations in clinical therapeutics:Explanation and rule acquisition capabilities of the MYCIN system," Computers and Biomedical Research, vol.8, pp.303-320,1975.
[19]Marakas,G. M,21世纪的决策支持系统,北京:清华大学出版社,2002.
[20]张德政,”中医专家系统技术综述及新系统实现研究,”计算机应用研究,Vol.24,pp.1-9,2007.
[21]M. A. Musen, Y. Shahar,E. H. Shortliffe, "Clinical decision-support systems," Biomedical Informatics, E. H. Shortliffe and J. J. Cimino, Eds., ed:Springer New York, pp.698-736,2006.
[22]M. M. E. Cabrera, Ernesto Ocampo, "Integration of rule based expert systems and case based reasoning in an acute bacterial meningitis clinical decision support system," International Journal of Computer Science and Information Security, vol.7(2), pp.112-118,2010.
[23]B. Kaplan, "Evaluating informatics applications--clinical decision support systems literature review," International Journal of Medical Informatics, vol. 64, pp.15-37,2001.
[24]P. J. G. Lisboa, "A review of evidence of health benefit from artificial neural networks in medical intervention," Neural Networks, vol.15, pp.11-39,2002.
[25]C. A. S. Carlos Ordonez, Levien de Braal, "Discovering interesting association rules in medical data," Proceedings of ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, pp.78-85,2000.
[26]W. C. Levy, D. Mozaffarian, D. T. Linker, S. C. Sutradhar, S. D. Anker, A. B. Cropp, et al., "The seattle heart failure model:prediction of survival in heart failure," Circulation, vol.113, pp.1424-1433,2006.
[27]A. Vellido,P. Lisboa, "Neural networks and other machine learning methods in cancer research," Computational and Ambient Intelligence.vol.4507, pp.964-971,2007.
[28]顾东风,”中国心力衰竭流行病学调查及其患病率,”中华心血管病杂志,Vol.31,pp.3-6,2003.
[29]http://www.nhlbi.nih.gov/health/dci/Diseases/Hf/HF_Diagnosis.html.
[30]C. Mueller, A. Scholer, K. Laule-Kilian, B. Martina, C. Schindler, P. Buser, et al., "Use of b-type natriuretic peptide in the evaluation and management of acute dyspnea," N Engl J Med, vol.350, pp.647-654,2004.
[31]S. Theodoridis,K. Koutroumbas,模式识别,北京:电子工业出版社,2008.
[32]焦立新,”评价指标标准化处理方法的探讨,”安徽农业技术师范学院学报,vol.13(3),pp.7-10,1999.
[33]J. W. Grzymala-Busse,M. Hu, "A comparison of several approaches to missing attribute values in data mining," presented at the Revised Papers from the Second International Conference on Rough Sets and Current Trends in Computing, pp.378-385,2001.
[34]乔珠峰,”缺失数据处理方法的比较研究,”计算机研究与发展,vol.43,pp.171-175,2006.
[35]S. Oba, M.-a. Sato, I. Takemasa, M. Monden, K.-i. Matsubara,S. Ishii, "A bayesian missing value estimation method for gene expression profile data," Bioinformatics, vol.19, pp.2088-2096,2003.
[36]孙振球,徐勇勇,医学统计学,北京:人民卫生出版社,2002.
[37]R. Gil-Pita,X. Yao, "Using a genetic algorithm for editing k-nearest neighbor classifiers," Intelligent Data Engineering and Automated Learning-IDEAL vol.4881, pp.1141-1150,2007.
[38]L. I. Kuncheva, "Editing for the k-nearest neighbors rule by a genetic algorithm," Pattern Recogn. Lett., vol.16, pp.809-814,1995.
[39]王静红,“决策树算法的研究及优化,”微机发展,vol.14,pp.30-32,2004.
[40]L. Rokach,O. Maimon, "Top-down induction of decision trees classifiers-a survey," Systems, Man, and Cybernetics, Part C:Applications and Reviews, IEEE Transactions, vol.35, pp.476-487,2005.
[41]M. Mehta, R. Agrawal,J. Rissanen, "SLIQ:a fast scalable classifier for data mining," presented at the Proceedings of the 5th International Conference on Extending Database Technology:Advances in Database Technology, pp.18-32,1996.
[42]J. R. Quinlan, "Simplifying decision trees," Int. J. Man-Mach. Stud., vol.27, pp.221-234,1987.
[43]N. Friedman, D.Geiger-M. Goldszmidt, "Bayesian network classifiers," Machine Learning, vol.29, pp.131-163,1997.
[44]F. Pernkopf, "Discriminative learning of Bayesian network classifiers," presented at the Proceedings of the 25th conference on Proceedings of the 25th IASTED International Multi-Conference:artificial intelligence and applications, Innsbruck, Austria, pp.422-427,2007.
[45]A. Zolnierek,B. Rubacha, "The empirical study of the naive Bayes classifier in the case of Markov chain recognition task," Computer Recognition Systems, Proceedings, pp.329-336,2005.
[46]A. K. Jain, M. Jianchang,K. M. Mohiuddin, "Artificial neural networks:a tutorial," Computer, vol.29, pp.31-44,1996.
[47]D. Gil, M. Johnsson, J. M. Garcia Chamizo, A. S. Paya,D. R. Fernandez, "Application of artificial neural networks in the diagnosis of urological dysfunctions," Expert Systems with Applications, vol.36, pp.5754-5760,2009.
[48]C. Cortes,V. Vapnik, "Support-vector networks," Machine Learning, vol.20, pp.273-297,1995.
[49]张永,迟忠先,米滢,”一类直接构造的模糊多类支持向量分类器,”计算机工程与应用,vol.44(8),pp.12-15,2008.
[50]H.-T. Lin, C.-J. Lin,R. Weng, "A note on Platt's probabilistic outputs for support vector machines," Machine Learning, vol.68, pp.267-276,2007.
[51]S. Lemeshow,D. W. Hosmer "A review of goodness of fit statistics for use in the development of logistic regression models," American Journal of Epidemiology, vol.115, pp.92-106,1982.
[52]http://zh.wikipedia.org/.
[53]K. Thangavel,A. Pethalakshmi, "Dimensionality reduction based on rough set theory:A review," Applied Soft Computing, vol.9, pp.1-12,2009.
[54]M. S. Yang, "A survey of fuzzy clustering," Mathematical and Computer Modelling, vol.18, pp.1-16,1993.
[55]A. Baraldi,P. Blonda, "A survey of fuzzy clustering algorithms for pattern recognition. I," Systems, Man, and Cybernetics, Part B:Cybernetics, IEEE Transactions on, vol.29, pp.778-785,1999.
[56]A. Baraldi,P. Blonda, "A survey of fuzzy clustering algorithms for pattern recognition. II," Systems, Man, and Cybernetics, Part B:Cybernetics, IEEE Transactions on, vol.29, pp.786-801,1999.
[57]L. C. Jain,C. P. Lim, "Advances in intelligent methodologies and techniques," Intelligent Systems and Technologies:Methods and Applications, vol.217, pp.3-28,2009.
[58]L. A. Zadeh, "Is there a need for fuzzy logic?," Information Sciences, vol.178, pp.2751-2779,2008.
[59]E. W. T. Ngai,F. K. T. Wat, "Fuzzy decision support system for risk analysis in e-commerce development," Decis. Support Syst., vol.40, pp.235-255,2005.
[60]M. Denai, M. Mahfouf,J. Ross, "A fuzzy decision support system for therapy administration in cardiovascular intensive care patients," Fuzzy Systems Conference, pp.1-6,2007.
[61]濮德璋,”一种新的模糊综合评价方法及其在实验室评估中的应用,”西南交通大学学报,vol.34,pp.6-10,1999.
[62]丁朝阳,”多级模糊综合评判法在气象服务保障能力评估中的应用,”气象科学,vol.25,pp.48-53,2005.
[63]http://i.mtime.com/920665/blog/5275253/.
[64]傅德印,”Q型系统聚类分析中的统计检验问题,”统计与信息论坛,vol.22,pp.10-14,2007.
[65]P. Langfelder, B. Zhang,S. Horvath, "Defining clusters from a hierarchical cluster tree:the Dynamic Tree Cut package for R," Bioinformatics, vol.24, pp.719-720,2008.
[66]谢可新,韩立兴,林友联,最优化方法,天津:天津大学出版社,1971.
[67]何新贵,模糊知识处理的理论与技术,北京:国防工业出版社,1998.
[68]王瑢,”主成分分析求权重在房地产顾客满意度评价中的应用,”市场研究,vol.26,pp.26-29,2010.
[69]陈贤,”主成分权重法在番茄果实商品性综合评价上的应用探讨,”吉林农业科学,vol.33(4),pp.49-52 2008.
[70]胡宝清,模糊理论基础,武汉:武汉大学出版社,2004.
[71]C. Orsenigo,C. Vercellis, "Evaluating Membership Functions for Fuzzy Discrete SVM," ed, pp.187-194,2007.
[72]H. J. Zimmermann, "Fuzzy set theory," Wiley Interdisciplinary Reviews: Computational Statistics, vol.2, pp.317-332,2010.
[73]R. Cardarelli,T. G. Lumicao, Jr, "B-type natriuretic peptide:a review of its diagnostic, prognostic, and therapeutic monitoring value in heart failure for primary care physicians," J Am Board Fam Pract, vol.16, pp.327-333,2003.
[74]X. Chunming, D. Feng, W. Yiqin, X. Zhaoxia, L. Guoping, X. Jin, et al., "Classification research on syndromes of TCM based on SVM," BMEI '09. 2nd International Conference, pp.1-4,2009.
[75]C.-C. Chang,C.-J. Lin, "LIBSVM:a library for support vector machines," Software available at http://www.csie.ntu.edu.tw/-cjlin/libsvm 2001.
[76]华伟,“心力衰竭非药物治疗的现状与发展方向,”中华医学杂志,vol.86,pp.1083-1085,2006.
[77]惠海鹏,“6分钟步行实验在充血性心力衰竭患者中的应用价值,”现代康复,vol.5,pp.3996-4001,2001.
[78]宇传华,徐勇勇,“ROC分析的基本原理,”中华流行病学杂志,vol.19,pp.413-415,1998.
[79]陈卫中,“ROC曲线中最佳工作点的选择,”中国卫生统计,vol.23,pp.157-158,2006.
[80]余海燕,“慢性心力衰竭早期诊断的研究进展,”心脑血管病防治,vol.10,pp.139-140,2010.
[81]G. D. Addio, M. Cesarelli, M. Romano, A. Accardo, G. Corbi, R. Maestri, et al., "Correlation between Fractal Behavior of HRV and Neurohormonal and Functional Indexes in Chronic Heart Failure," ed:Springer Berlin Heidelberg, vol.29, pp.53-56,2010.
[82]E. Choi,C. Lee, "Feature extraction based on the bhattacharyya distance," Pattern Recognition, vol.36, pp.1703-1709,2003.