【作者】 杨桂秋；

【导师】 宁钢民；

【作者基本信息】 浙江大学 ， 生物医学工程， 2011， 硕士

【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。更多还原

【Abstract】 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.更多还原