基于支持向量机的诊断方法研究

根据支持向量机原理,对线性可分与线性不可分两种情况分别建立了分类模型,模型的求解转化为一个二次规划问题,在选用径向基核函数的参数时运用网格搜索的方法进行选取最优参数。在应用到乳房肿瘤的医疗诊断中,准确率为93.00%,较以前的方法有了明显的提高。     

浅谈疲劳诊断与恢复的中医学方法

本文运用中医学理论,提出了诊断运动性疲劳及其恢复的简易中医学方法。     

上消化道出血49例胃超声影象分析

目的分析上消化道出血胃B超图象特征,探讨B超对上消化道出血及其病因诊断的意义.方法;选择上消化道出血活动期的位院患者49例,分别于空腹及饮水后依次探查贲门、胃体、胃窦、十二指肠及其邻近器官,记录图像,并结合内镜病理及X线结果进行分析.结果49例中.B超检出相关疾病41例,命中37例;检出率及准确率分别为83.7%和75.5%,X线报告32例,命中29例,检出率及准确率分别为65.3%和59.2%,统计分析结果显示该两种检查方法有显著差异(P＜0.05).结论B型超声可作为上消化道出血病因诊断较可靠的方法.     

电控发动机故障检测与诊断

本文介绍了电控发动机故障检测与诊断的基本原则和方法。     

Study of clinical features of amyloid angiopathy hemorrhage and hypertensive intracerebral hemorrhage

Objective: The purpose of this study was to differentiate between cerebral amyloid angiopathy (CAA) and hypertension (HTN) based on hemorrhage pattern interpretation. Methods: From June 1994 to Oct., 2000, 83 patients admitted to our service with acute intracerebral hemorrhage (ICH) were investigated retrospectively; 41 patients with histologically proven diagnosis of cerebral amyloid angiography and 42 patients with clear history of hypertension were investigated. Results: Patients with a CAA-related ICH were significantly older than patients with a HTN-related ICH (74.0years vs 66.5 years, P＜0.05). There was a significantly higher number ofhematomas≥30 ml in CAA (85.3%) when compared with HTN (59.5%). No basal ganglional hemorrhage was seen in CAA, but in 40.5% in HTN. In CAA-related ICH, subarachnoid hemorrhage (SAH) was seen in 26 patients (63.4%) compared to only 11 patients (26.2%) in HTN-related ICH.Intraventricular hemorrhage was seen in 24.4% in CAA, and in 26.2% in HTN. Typical features of CAA-related ICH included lobar distribution affecting mainly the lobar superficial areas, lobulated appearance, rupture into the subarachnoid space, and secondary IVH from the lobar hemorrhage. More specifically, multiplicity of hemorrhage, bilaterality, and repeated episodes also strongly suggest the diagnosis of CAA. Multiple hemorrhages, defined as 2 or more separate hematomas in multiple lobes, accounted for 17.1% in CAA-related ICH. Conclusion: There are certain features in CAA on CT and MRI and in clinical settings. To some extent, these features may contribute to distinguishing CAA from HTN related ICH.     

多元智能诊断存在的问题与对策

介绍了多元智能诊断研究的现状,指出了目前多元智能诊断存在的问题,并针对存在的问题从诊断题目设计、评分标准设计、诊断系统设计以及诊断结果分析等四个方面提出解决问题的对策。     

An integrated approach utilizing proteomics and bioinformatics to detect ovarian cancer

INTRODUCTION Ovarian cancer is the most lethal gynecologicmalignancy. Poor survival rates are mainly attribut-able to late diagnosis. Most patients at diagnosis haveadvanced stage disease. The 5-year survival rate forlate clinical stage ovarian cancer is only 25%, but forearly stage disease, the survival rate can be as high as90%. CA125, the most widely used biomarker forovarian cancer, does not have a satisfying positivepredictive value. In early stage ovarian cancer,40%–50% pati…     

Science Letters:Serum protein fingerprinting coupled with artificial neural network distinguishes glioma from healthy population or brain benign tumor

To screen and evaluate protein biomarkers for the detection of gliomas(Astrocytoma grade Ⅰ-Ⅳ) from healthy in-dividuals and gliomas from brain benign tumors by using surface enhanced laser desorption/ionization time of flight mass spec-trometry(SELDI-TOF-MS)coupled with an artificial neural network(ANN)algorithm.SELDI-TOF-MS protein fingerprinting ofserum from 105 brain tumor patients and healthy individuals,included 28 patients with glioma(Astrocytoma Ⅰ-Ⅳ),37 patientswith brain benign tumor,and 40 age-matched healthy individuals.Two thirds of the total samples of every compared pair as trainingset were used to set up discriminating patterns,and one third of total samples of every compared pair as test set were used tocross-validate;simultaneously,discriminate-cluster analysis derived SPSS 10.0 software was used to compare Astrocytoma gradeⅠ-Ⅱ with grade Ⅲ-Ⅳ ones.An accuracy of 95.7%,sensitivity of 88.9%,specificity of 100%,positive predictive value of 90% andnegative predictive value of 100% wer     

基于粗糙集正域的医疗决策表约简算法

医学数据通常属性较多,这在很大程度上限制了信息系统对医疗数据的挖掘效率。通过分析粗糙集正域的相关思想,结合医学领域数据的特点,提出一种基于粗糙集正域的医疗决策表约简算法,并将其应用在医学诊断中。通过实例验证了该算法在医疗决策表约简中的正确性和有效性,具有一定的实用价值。     

对少数民族地区高校图书馆馆藏资源利用率的调查分析——以喀什师范学院为例

图书馆利用率体现了图书馆是否富有生机,是否有存在的价值。因此,如何提高图书馆的利用率是图书馆人共同关心的问题,也是亟待解决的问题。论文对喀什师范学院图书馆利用率进行调查,以此为切入点对少数民族高校图书馆的利用率进行了分析,并提出了合理利用图书馆资源的相应措施。