A Radial Basis Function Neural Network (RBFNN) Approach for Structural Classification of Thyroid Diseases

The thyroid is a gland that controls key functions of body. Diseases of the thyroid gland can adversely affect nearly every organ in human body. The correct diagnosis of a patient’s thyroid disease clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. This study investigates Multilayer Perceptron Neural Network (MLPNN) and Radial Basis Function Neural Network (RBFNN) for structural classification of thyroid diseases. A data set for 487 patients having thyroid disease is used to build, train and test the corresponding neural networks. The structural classification of this data set was performed by two expert physicians before the input variables and results were fed into the neural networks. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. Regarding the evaluation data, the trained RBFNN model outperforms the corresponding MLPNN model. This study demonstrates the strong utility of an artificial neural network model for structural classification of thyroid diseases.     

Diagnosis of Epilepsy from Electroencephalography Signals Using Multilayer Perceptron and Elman Artificial Neural Networks and Wavelet Transform

In this study, it has been intended to perform an automatic classification of Electroencephalography (EEG) signals via Artificial Neural Networks (ANN) and to investigate these signals using Wavelet Transform (WT) for diagnosing epilepsy syndrome. EEG signals have been decomposed into frequency sub-bands using WT and a set of feature vectors which were extracted from the sub-bands. Dimensions of these feature vectors have been reduced via Principal Component Analysis (PCA) method and then classified as epileptic or healthy using Multilayer Perceptron (MLP) and ELMAN ANN. Performance evaluation of the used ANN models have been carried out by performing Receiver Operation Characteristic (ROC) analysis.     

A Software Tool for Determination of Breast Cancer Treatment Methods Using Data Mining Approach

In this work, breast cancer treatment methods are determined using data mining. For this purpose, software is developed to help to oncology doctor for the suggestion of application of the treatment methods about breast cancer patients. 462 breast cancer patient data, obtained from Ankara Oncology Hospital, are used to determine treatment methods for new patients. This dataset is processed with Weka data mining tool. Classification algorithms are applied one by one for this dataset and results are compared to find proper treatment method. Developed software program called as “Treatment Assistant” uses different algorithms (IB1, Multilayer Perception and Decision Table) to find out which one is giving better result for each attribute to predict and by using Java Net beans interface. Treatment methods are determined for the post surgical operation of breast cancer patients using this developed software tool. At modeling step of data mining process, different Weka algorithms are used for output attributes. For hormonotherapy output IB1, for tamoxifen and radiotherapy outputs Multilayer Perceptron and for the chemotherapy output decision table algorithm shows best accuracy performance compare to each other. In conclusion, this work shows that data mining approach can be a useful tool for medical applications particularly at the treatment decision step. Data mining helps to the doctor to decide in a short time.     

A Radial Basis Function Neural Network Model for Classification of Epilepsy Using EEG Signals

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient’s epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify epilepsy groups such as partial and primary generalized epilepsy by using Radial Basis Function Neural Network (RBFNN) and Multilayer Perceptron Neural Network (MLPNNs). Four hundred eighteen patients with epilepsy diagnoses according to International League against Epilepsy (ILAE 1981) were included in this study. The correct classification of this data was performed by two expert neurologists before they were executed by neural networks. The neural networks were trained by the parameters obtained from the EEG signals and clinic properties of the patients. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. According to test results, RBFNN (total classification accuracy = 95.2%) has classified more successfully when compared with MLPNN (total classification accuracy = 89.2%). These results indicate that RBFNN model may be used in clinical studies as a decision support tool to confirm the classification of epilepsy groups after the model is developed.     

Autoassociative MLP in Sleep Spindle Detection

Spindles are one of the most important short-lasting waveforms in sleep EEG. They are the hallmarks of the so-called Stage 2 sleep. Visual spindle scoring is a tedious workload, since there are often a thousand spindles in one all-night recording of some 8 hr. Automated methods for spindle detection typically use some form of fixed spindle amplitude threshold, which is poor with respect to inter-subject variability. In this work a spindle detection system allowing spindle detection without an amplitude threshold was developed. This system can be used for automatic decision making of whether or not a sleep spindle is present in the EEG at a certain point of time. An Autoassociative Multilayer Perceptron (A-MLP) network was employed for the decision making. A novel training procedure was developed to remove inconsistencies from the training data, which was found to improve the system performance significantly.     

基于竞争风险模型的北京市老年人群心血管疾病短期风险评估

目的 在考虑"竞争事件"的前提下,对北京市老年人群心血管疾病(cardiovascular disease,CVD)进行5年的风险评估。方法 基于传统的心血管疾病影响因素年龄、糖尿病、吸烟、婚姻状况、体质量指数、血压(blood pressure, BP)、总胆固醇(total cholesterol,TC)、高密度脂蛋白胆固醇(high-density lipoprotein cholesterol, HDL-C),构建竞争风险模型,计算未来5年心血管疾病的绝对风险,通过受试者工作特征曲线(receiver operating characteristic curve,ROC)及依时受试工作者曲线下面积(areas under the ROC curve, AUC)值来衡量模型的判别能力,采用校正图来衡量模型的校正度。经过Bootstrap重抽样技术对风险预测模型进行内部验证以减少过度拟合偏倚。结果 1992年基线检查无心血管疾病者共1 775人,其中男性886人(49.92%),女性889人(50.08%),至2012年末随访结束,共有473人死于心血管疾病,693人死于非心血管疾病,609人存活或失访。男性与女性心血管疾病的风险评分总分分别为65分和62分,最佳切点分别为34分和30分。预测模型具有较好的判别能力与校正度。结论 利用心血管疾病的传统危险因素,借助竞争风险模型,构建了北京市老年人群心血管疾病的短期风险评估工具,为有效筛查心血管疾病的高危人群提供了科学依据和技术手段。     

脂蛋白a在老年脑血管病急性期中的检测及临床意义

目的 观察脂蛋白-a[ LP(a)]水平在老年脑血管病急性期(CVD)患者血清中的测定,探讨其在老年CVD患者中的临床意义.方法 采用乳胶比浊法对60(男34例,女26例)例老年CVD患者血清中LP(a)进行测定,然后分为急性期组与稳定期组和男性组与女性组进行比较.结果 Lp(a)的浓度在老年CVD的急性期远高于稳定期...     

伴抑郁或焦虑症老年心血管病患者性别及心律失常分析

目的：研究伴抑郁或焦虑症老年心血管病（CVD）患者的性别差异及心律失常发生情况，探讨不同心理状态下各指标有无差别。方法：收集伴抑郁或焦虑症老年CVD患者（A组）、不伴抑郁或焦虑症的老年CVD患者（B组）的性别及动态心电图（DCG）资料，分析各组性别、心律失常发生种类和数量以及心率变异性（HRV）的差异。结果：A组中伴抑郁的老年女性CVD患者的评分与男性相比差异有统计学意义（P〈0.05）。Holter监测显示，A组患者的室性心律失常、房性心律失常、缺血性ST—T改变以及HRV减低的发生率明显高于B组，差别有统计学意义（P〈0.05）。结论：伴抑郁症老年女性CVD患者的程度较重，焦虑症在男女性别上无明显差异。伴抑郁痒或焦虑痒老年心血管疾病者易发牛窜件和房性心律失常，且HRV明显减低。     

Effect of elevated total cholesterol level and hypertension on the risk of fatal cardiovascular disease: a cohort study of Chinese steelworkers

Background  Increased blood pressure and elevated total cholesterol (TC) level are the two most important modifiable risk factors of cardiovascular disease (CVD) in the world. Hypertension and hypercholesterolemia co-exist more often than would be expected and whether there is a synergistic impact on fatal CVD between elevated TC and hypertension need to be further examined in Chinese population.

Methods  We conducted a cohort study which recruited 5092 Chinese male steelworkers aged 18–74 years in 1974–1980 and followed up for an average of 20.84 years. Totally 302 fatal CVD events were documented by the year of 2001. Cox proportional hazards regression models were undertaken to adjust for baseline variables with fatal CVD events as the outcome variable. Additive interaction model was used to evaluate the interaction between elevated TC and hypertension.

Results  Hypercholesterolemia and hypertension were significantly associated with an increased hazard ratio (HR) of fatal CVD (1.67 (95% CI 1.18–2.38) and 2.91 (95% CI 2.23–3.80) respectively. Compared to participants with normotension and TC <240 mg/dl, the HRs were 1.11 (95% CI 0.56–2.21), 2.74 (95% CI 2.07–3.64) for hypercholesterolemia and hypertension respectively, and 5.51 (95% CI 3.58–8.46) for participants with both risk factors. There was an additive interaction with a 2.65 (95% CI 0.45–4.85) relative excess risk (RERI) between hypercholesterolemia and hypertension on CVD.

Conclusion  We found that the risk of fatal CVD was significantly associated with an additive interaction due to hypercholesterolemia and hypertension besides a conventional main effect derived from either of them, which highlights that the prevention and treatment of both risk factors might improve the individual risk profile thus reduce the CVD mortality.

     

常见心脑血管疾病患者代谢综合征患病情况调查

目的 :探讨常见心脑血管疾病患者代谢综合征的患病情况。方法 :根据 6 5 7例常见心脑血管疾病患者(男性 35 4例 ,女性 30 3例 ,年龄 33岁～ 89岁 )的各代谢因素指标 ,计算代谢综合征及各因素的标准化发病率。结果 :心脑血管病人超重、高空腹血糖 (FPG)、高血压、高胆固醇 (TC)、高甘油三酯 (TG)、低高密度脂蛋白胆固醇 (HDL - C)、代谢综合征的发病率分别为 36 .5 3%、37.4 4 %、80 .37%、2 4 .2 0 %、5 6 .6 2 %、10 .5 0 %、4 2 .0 1%。结论 :常见心脑血管疾病患者具有较高的代谢综合征及相关疾病的患病率     

社区老年人群性激素结合球蛋白与心血管发病风险的关联性

 目的  探讨社区老年人群中性激素结合球蛋白(sex hormone binding globulin,SHBG)与心血管疾病(cardiovascular disease,CVD)之间的相关性。方法  于2014年选取上海市宝山区友谊社区1 916例老年人群(男796例、女1 120例),收集基础的流行病学资料并采集空腹静脉血进行检测,计算得到10年Framingham风险积分。将肥胖、收缩压、空腹血糖、脂类浓度及超敏C反应蛋白作为心血管疾病风险因子,Framingham风险积分作为心血管疾病事件预测危险积分,分析SHBG与它们之间的相关性。结果  存在心血管病史人群的SHBG均值低于不存在心血管病史人群(P<0.001);男性SHBG与腰围、臀围、BMI指数、收缩压、胆固醇、三酰甘油、高密度脂蛋白胆固醇、载脂蛋白A、超敏C反应蛋白的相关系数分别为-0.312、-0.307、-0.266、-0.113、0.155、-0.277、0.510、0.394、-0.130(P<0.01);女性SHBG与腰围、臀围、BMI指数、空腹血糖、胆固醇、三酰甘油、高密度脂蛋白胆固醇、载脂蛋白A和超敏C反应蛋白的相关系数分别为-0.236、-0.248、-0.168、-0.183、0.135、-0.264、0.445、0.358、-0.295 (P<0.001);SHBG水平的降低与Framingham积分的升高存在一致性(κ=0.062,P<0.001),且SHBG水平的升高会降低10年内CVD的发病风险(P<0.01)。结论  该社区老年人群基线SHBG水平与CVD风险因子之间存在负相关性,与CVD保护因子之间存在正相关性,并且低水平SHBG预示着更高的CVD发病风险。     

Classification of MCA Stenosis in Diabetes by MLP and RBF Neural Network

For the classification of Middle Cerebral Artery (MCA) stenosis, Doppler signals have been received from the diabetes and control group by using 2 MHz Transcranial Doppler. After the Fast Fourier Transform (FFT) analyses of the Doppler signals, Power Spectrum Density (PSD) estimations have been made and Multilayer Perceptron (MLP) and Radial Basis Function (RBF) have been dealt to apply to the neural networks. PSD estimations of Doppler signals received from MCA of 104 subjects have been successfully classified by MLP (correct classification = 94.2%) and RBF (correct classification = 88.4%) neural network. As we have seen in the area under ROC curve (AUC), MLP neural network (AUC = 0.934) has classified more successfully when compared with RBF neural network (AUC = 0.873).     

成人斯蒂尔病男女有何不同——101例成人斯蒂尔病患者临床分析

目的探讨不同性别成人斯蒂尔病患者临床表现和实验室检验结果的差异。方法收集1986年12月～2006年12月我院101例成人斯蒂尔病患者资料,分为男性组(23例)和女性组(78例),分析比较一般资料及实验室检验结果的差异。结果成人斯蒂尔病住院患者男∶女为1∶3.39(23vs78)。男性组患者在夏季住院的比例多于女性组,在冬季少于女性,差异有显著意义(P<0.05)。临床表现中女性组以皮疹为首发症状,男性组患者以发热为首发症状,男性组咽痛、肌痛、肝大者多于女性组,2组比较差异有显著意义。实验室检测指标中女性组ESR、CRP升高程度较男性组高(P<0.05)。结论不同性别成人斯蒂尔病患者的发病季节、某些临床表现及实验室检查结果存在一定差异。     

Predictive value of serum uric acid on cardiovascular disease and all-cause mortality in urban Chinese patients

Background The association between increased serum uric acid （SUA） levels and cardiovascular risk has been debated for decades. Several large studies have provided conflicting results regarding the clinical significance of elevated SUA levels in cardiovascular disease （CVD） or cerebrovascular disease. The aim of this study was to investigate the relationship between SUA and CVD and all-cause mortality and their potential diagnostic value. Methods A total of 3570 in-patients ranging in age from 56 to 95 years （mean （67.36_＋11.36） years） were selected from 20 hospitals in Beijing and Shanghai. A carefully designed questionnaire was used to gather baseline data of each patient All patients were divided into two main groups according to their SUA levels： high SUA and normal SUA groups. Serum indices and other important parameters were measured. Results Compared with normal SUA group, high SUA group had significant difference in systolic blood pressure （SBP）, total cholesterol （TC）, triglyceride （TG）, high density lipoprotein cholesterol （HDL-C）, body mass index （BMI）, and age （P 〈0.05 or P 〈0.01）. High SUA prevailed in female and patients with history of essential hypertension, while history of smoking and diabetes showed no significant difference between two groups. All-cause and CVD mortality occurred more frequently in high SUA group than in normal SUA group. In the accumulative survival analysis, high SUA group had lower survival rate than normal SUA group both in CVD and all-cause mortality. COX regression analysis indicated that the history of smoking, age and high SUA were independent risk factors for the development of CVD. Conclusions These preliminary observations suggest that patients with high SUA levels would face higher risk of mortality. SUA measurement may be applied as a routine predictor for clinical assessment.     

微型营养评价法在老年心血管疾病住院患者营养不良风险评价中的应用

目的：探讨微型营养评价法（MNA）在老年心血管疾病（CVD）住院患者营养不良风险评价中的应用。方法运用 MNA 法测定316例老年 CVD 住院患者的 MNA 总分,根据 MNA 总分 评 估 患 者 营 养 状 况。结果营养不良组52例（16．46％）,营养不良风险组60例（18．99％）,营养状况良好组204例（64．56％）;女性老年患者营养风险及营养不良发生率均高于男性患者,差异有统计学意义（P ＜0．01）;高龄患者（≥80岁）营养风险及营养不良发生率均高于低龄患者（60～＜80岁）,但差异无统计学意义（P ＞0．05）;农村患者营养风险及营养不良发生率均高于城镇居住患者,且差异有统计学意义（P ＜0．05）。结论老年 CVD 患者营养不良风险发生率较高,可在老年 CVD 住院患者中应用 MNA 进行营养状况监测和营养不良风险的早期筛查。     

热浪对居民循环系统疾病死亡影响的病例交叉研究

目的 探讨浙江省嘉兴市热浪对居民循环系统疾病日死亡人数的影响。 方法 本研究中热浪定义为日最高温度不低于35 ℃,且持续不少于3 d。采用时间分层的病例交叉设计方法,调整每日平均气温、降水量、平均风速、平均气压和空气污染指数建立条件Poisson回归模型,分析嘉兴市2008~2011年热浪与居民循环系统疾病死亡的关系,并分析滞后效应。 结果 2008~2011年共出现6次热浪。滞后2 d时热浪对循环系统疾病死亡数影响的效应值最大,RR值为1.342(95%CI:1.081~1.667)。热浪对≥65岁老年人在滞后2 d时RR值最大,为1. 296(95%CI: 1.027~1.636),对女性在滞后2 d时RR值最大,为1. 407(95%CI: 1.021~1.937)。 结论 热浪会增加循环系统疾病死亡风险,且存在滞后效应;≥65岁老年人和女性为脆弱人群。     

Predicted 10-year Cardiovascular Disease Risk and Its Association with Sleep Duration among Adults in Beijing-Tianjin-Hebei Region,China

Objective The study aims to predict 10-year cardiovascular disease (CVD) risk and explore its association with sleep duration among Chinese urban adults. Methods We analyzed part of the baseline data of a cohort that recruited adults for health screening by cluster sampling. The simplified Pittsburgh Sleep Quality Index (PSQI) and Framingham 10-year risk score (FRS) were used to measure sleep duration and CVD risk. Demographic characteristics, personal history of chronic diseases, lifestyle factors were collected using a questionnaire. Height, weight, total cholesterol (TC), and high-density lipoprotein cholesterol (HDL-C) were also measured. Multiple logistic regression models were performed to explore the association of sleep duration with the predicted CVD risk. Results We included 31, 135 participants (median age 44 years, 53.02％ males) free of CVD, cerebral stroke, and not taking lipid-lowering agents. Overall, 14.05％, and 25.55％ of participants were at medium and high predicted CVD risk, respectively. Short sleep was independently associated with increased odds of medium to high risk of predicted 10-year CVD among males (OR = 1.10; 95％ CI:1.01–1.19) and increased odds of medium to high and high risk of predicted 10-year CVD among females (OR = 1.23; 95％ CI: 1.08–1.40; OR = 1.27; 95％ CI: 1.11–1.44). In contrast, long sleep had no association with cardiovascular risk. Conclusion A substantial number of adults free of CVD were at high 10-year CVD risk. Short sleep was associated with increased odds of predicted CVD risk.     

Investigation of cardiovascular risk factors in type 2 diabetes in a rural Australian Division of General Practice

OBJECTIVE: To examine the changes in cardiovascular disease (CVD) risk factors for a cohort of patients with type 2 diabetes in general practice. DESIGN AND SETTING: A 4-year retrospective cohort study using extracted data from an active Division of General Practice diabetes register in Australia. PARTICIPANTS: 628 patients (297 female; 331 male) with type 2 diabetes who participated in the diabetes program of the Southern Highlands Division of General Practice and for whom evaluation data were recorded each year from 2002 to 2005. MAIN OUTCOME MEASURES: Changes in the following CVD risk factors over time: body mass index (BMI), serum lipid levels (total cholesterol [TC], low-density lipoprotein cholesterol [LDL-C], high-density lipoprotein cholesterol [HDL-C], total triglycerides [TG]), systolic and diastolic blood pressure (BP), and glycated haemoglobin (HbA(1c)) level. RESULTS: After adjusting for age, sex, duration and clustering, there was significant improvement in serum lipid levels (TC and LDL-C; P < 0.05) over time; and there was no significant change in BP, HbA(1c) level or BMI. Older patients had significantly worse systolic BP, but significantly better BMI and lipid levels than younger patients. Longer duration of diabetes was associated with worse systolic BP and HbA(1c) level, but better HDL-C level. People with higher BMI were likely to have worse systolic BP, and HDL-C and HbA(1c) levels, but better TC level than those with lower BMI. CONCLUSIONS: Improving BP, HbA(1c) level and BMI may be more difficult than improving lipid levels. There is a need for more intensive and comprehensive interventions to reduce the total risk of CVD.     

多囊肝(附一例报告及文献复习)

本文报导一例多囊肝,结合国内报导的75例多囊肝的文献复习,对多囊肝的病因、发病原理、临床表现及诊断等作进一步的探讨。多囊肝系少见病,一般是小儿先天性的,其临床症状多在30岁后出现,女性多于男性,男女之比是1:4～5。临床症状可表现为慢性胆囊炎及肿瘤症状。诊断主要依靠 CT、超声检查及剖腹探查。     

Association between Metabolic Syndrome and Carotid Atherosclerosis: A Cross-sectional Study in Northern China

ObjectiveIncreased carotid artery intima-media thickness (CIMT) and carotid plaque as manifestations of carotid atherosclerosis have been used as markers of cardiovascular disease (CVD). The components of metabolic syndrome (MetS) are linked to CVD, but the association between MetS and CVD is controversial.MethodsA total of 8,933 Chinese adults aged 40 years or older from 2010 to 2014 were selected from the Jidong and Kailuan communities. MetS was defined by the International Diabetes Federation criteria. CIMT and carotid plaque were measured using color Doppler ultrasound. Logistic regression models were used to assess the association of MetS with carotid plaque and CIMT.ResultsMetS was found among 3,461 (3,461/8,933) participants. The odds ratio and 95% confidence internal (CI) for carotid plaques in participants with MetS was 1.16 (1.03–1.30). The risk of carotid plaques increased with the number of MetS components. The average CIMT was higher in participants with MetS (β = 0.020, 95% CI, 0.014–0.027) and in participants with more MetS components.ConclusionIndividuals with MetS are at an increased risk for carotid atherosclerosis compared to those without MetS.