出血性脑梗死危险因素的Logistic回归分析

目的探讨出血性脑梗死的危险因素。方法根据专业知识确定与出血性脑梗死有关的因素,采用非条件Logistic回归确定危险因素。结果大面积梗死灶、使用抗凝剂或溶栓治疗、糖尿病史是出血性脑梗死的独立危险因素,与年龄、高血压史、高血脂关系不大。结论大面积脑梗死、使用抗凝剂或溶栓、糖尿病患者发生梗死后出血的几率增大,及时行影像学检查可以早期发现。     

肥胖与胆石病的多因素条件Logistic回归分析

目的探讨肥胖与结石病发病的关系。方法采用调查表的方式对1997年住院手术确诊为结石病的病人进行回顾性调查，内容包括：年龄、性别、体重、身高、是否吃早餐。对调查表进行多因素logstic统计分析。结果分析结果表明我们调查了我院102例结石病患者和101名正常人发现肥胖、女性、不经常吃早餐、饮用高硬度的水均是结石病的危险因紊，对那些长时间不吃早餐的人更容易患结石病，（相对危险度OR〉40．139）。结论我们建议今后应注意膳食营养的均衡，保持标准体重，饮用卫生水。     

结直肠癌手术死亡相关因素分析

目的:研究旨在探讨结直肠癌手术死亡相关的临床病理影响因素.方法:回顾中山大学肿瘤防治中心1964年1月至2004年12月经手术治疗的4498例结直肠癌患者的临床病理资料,应用单因素和多因素Logistic回归分析手术死亡的相关影响因素.结果:全组手术死亡者共62例,手术死亡率为1.38%,主要死亡原因为多器官功能衰竭、中毒性休克、心血管疾病、急性肾功能衰竭、吻合口漏等.单因素分析显示,性别、术前基础疾病、术前合并症、腹水、手术年代、手术性质、Dukes分期、术后并发症等为影响手术死亡的因素,而年龄、肿瘤部位、组织类型、病理分级与手术死亡无关.多因素分析表明,术前基础疾病、术前合并症、腹水、手术年代、手术性质、Dukes分期、术后并发症是结直肠癌手术死亡的独立影响因素.结论:术前基础疾病、术前合并症、腹水、手术年代、手术性质、Dukes分期、术后并发症是结直肠癌手术死亡的独立影响因素.     

安氏Ⅲ类错畸形病因的logistic分析

目的研究引起安氏Ⅲ类错牙合畸形的病因。方法对50例安氏Ⅲ类错牙合患者和50例正常牙合人作病因问卷调查,将结果用logistic法分析,提取有效病因。结果共有慢性扁桃体炎、遗传因素、咬上唇3项病因进入方程。结论按贡献大小,长期慢性扁桃体炎、经常咬上唇和遗传因素是导致安氏Ⅲ类错牙合畸形的危险因素。     

高血压病危险因素研究

本文对高血压病病人及对照的生活习惯、个人嗜好、精神因素等15个因素进行了1:1配比病例对照研究及 Logistic 回归分析,同时调查厂遗传因素和高血压病的关系。结果表明:超体重、发病前二年受应激事件刺激、母亲高血压史为高血压病的危险因素。高血压病遗传度35.58%,提示遗传因素在该病的发生过程中不起主要作用。     

A preliminary statistical model for identifying repeaters of parasuicide

This paper presents a statistical model constructed using logisticregression to identify those at high-risk of repeating parasuicide. Thesubjects in the study are Cork city residents who exhibited parasuicidalbehaviour between 1 January and 30 June 1995. Repetition of the behaviourwithin six months of the index episode distinguishes repeaters fromnon-repeaters. The model was designed so that it could be used bynon-clinicians and hence does not require information relating topsychiatric diagnosis or use of psychiatric services. The proportion ofsubjects correctly classified remained stable across a range of cut-pointprobabilities (mean = 86%, range: 83.9–87.5%). Using acut-point of 0.2, 96% of repeaters and 81% of non-repeaters were correctly classified. Using 0.45 led to the correct identification of81% of repeaters and 90% of non-repeaters. If these highlevels of sensitivity and specificity are maintained in validation tests onfuture cohorts in Cork city then the model could form the basis of anintervention programme designed to prevent the repetition of parasuicide.     

阿拉善黄鼠疫源地动物鼠疫预报的数学模型

根据我国阿拉善黄鼠鼠疫自然疫源地1981～1993年鼠疫监测资料，采用多元逐步曲线回归分析，建立了预报阿拉善黄鼠鼠疫流行的数学模型，其拟合率为100%，并得出影响鼠疫流行的主要因子为黄鼠密度和巢蚤指数。     

鼻咽癌病因学的病例—对照研究

本文以病例—对照的方法探讨了在黑龙江省与鼻咽癌发生有关的危险因素。调查鼻咽癌病例及对照共127对。在单因素与条件Logistic回归分析中均表明幼儿期食咸鱼(OR=5.5, χ²=4.92, P<0.05)及长期生活在烧煤的环境中(OR=1.894, χ²=4.655, P<0.05)可能与鼻咽癌的发生有关。此外,条件Logistic回归分析还发现,鼻窦炎病史也可能与鼻咽癌的发生有联系(B=1.385, exp(B)=3,995, P<0.1)。在对病例及对照的一级亲属患恶性肿瘤情况的调查中发现,鼻咽癌病例组有肿瘤家族史者多于对照组,其差异有统计学意义(χ²=10.32, P<0.01)。     

Evaluating risk factors associated with severe hypoglycaemia in epidemiology studies—what method should we use?

AIMS: To determine the most appropriate regression models to use when assessing risk factors for severe hypoglycaemia and to investigate the impact of model misspecification and its clinical implications. METHODS: A total of 1229 children with Type 1 diabetes (mean age 11.7 years sd 4.1), of which 605 (49.2%) were males, were studied. Prospective assessment of severe hypoglycaemia (an event leading to loss of consciousness or seizure) was made over the 9-year period, 1992-2001. Patients were seen every 3 months and episodes of hypoglycaemia along with clinical data were recorded. Over 70% of children never experienced a severe hypoglycaemic event. Data were analysed using the Poisson regression, negative binomial, zero-inflated Poisson (ZIP) and zero-inflated negative binomial (ZINB) models. The over-dispersion and likelihood ratio statistics were calculated and the analytical methods compared. RESULTS: The Poisson regression model did not fit the data well. The negative binomial and the zero inflated Poisson and negative binomial models fitted the data better than Poisson. CONCLUSIONS: The commonly used Poisson regression models to analyse hypoglycaemia epidemiology may lead to biased parameter estimates and incorrect determination of risk factors for hypoglycaemia. We recommend the use of the negative binomial or zero inflated models to examine any risk factors associated with severe hypoglycaemia. Careful consideration must be given to the interpretation of hypoglycaemia surveys and their analysis.