神经网络模型和logistic回归在预测慢性阻塞性肺疾病中的应用研究

目的 应用神经网络和logistic回归分析方法建立慢性阻塞性肺疾病(chronic obstructive pulmonary disease,COPD)数学预测模型.方法 通过横断面调查收集2015年湖北省2 400人的COPD流行病学资料,按7∶3的比例随机分为训练组与验证组,应用神经网络和logistic回归分...     

A new synthesis analysis method for building logistic regression prediction models

Synthesis analysis refers to a statistical method that integrates multiple univariate regression models and the correlation between each pair of predictors into a single multivariate regression model. The practical application of such a method could be developing a multivariate disease prediction model where a dataset containing the disease outcome and every predictor of interest is not available. In this study, we propose a new version of synthesis analysis that is specific to binary outcomes. We show that our proposed method possesses desirable statistical properties. We also conduct a simulation study to assess the robustness of the proposed method and compare it to a competing method. Copyright © 2014 John Wiley & Sons, Ltd.     

Comparison of logistic regression and neural network analysis applied to predicting living setting after hip fracture

PURPOSE: Describe and compare the characteristics of artificial neural networks and logistic regression to develop prediction models in epidemiological research. METHODS: The sample included 3708 persons with hip fracture from 46 different states included in the Uniform Data System for Medical Rehabilitation. Mean age was 75.5 years (sd=14.2), 73.7% of patients were female, and 82% were non-Hispanic white. Average length of stay was 17.0 days (sd=10.6). The primary outcome measure was living setting (at home vs. not at home) at 80 to 180 days after discharge. RESULTS: Statistically significant variables (p <.05) in the logistic model included follow-up therapy, sphincter control, self-care ability, marital status, age, and length of stay. Areas under the receiver operating characteristic curves were 0.67 for logistic regression and 0.73 for neural network analysis. Calibration curves indicated a slightly better fit for the neural network model. CONCLUSIONS: Follow-up therapy and independent bowel and/or bladder function were strong predictors of living at home up to 6 months after hospitalization for hip fracture. No practical differences were found between the predictive ability of logistic regression and neural network analysis in this sample.     

Analysis of proportionate mortality data using logistic regression models

When only proportionate mortality data are available to an investigator studying the effect of an exposure on a particular cause of death, controls must be selected from among persons dying of other causes believed to be uninfluenced by the exposure under study. When qualitative or quantitative estimates of exposure history can be obtained for the deceased individuals, it is shown that one can use logistic regression models for the mortality odds to efficiently estimate the effect of exposure while controlling for relevant confounding factors by incorporating a priori information on baseline mortality rates available from US life tables. The proposed method is used to reanalyze data from a cohort of arsenic-exposed workers in a Montana copper smelter.     

Transition models for change-point estimation in logistic regression

Although a wide variety of change-point models are available for continuous outcomes, few models are available for dichotomous outcomes. This paper introduces transition methods for logistic regression models in which the dose-response relationship follows two different straight lines, which may intersect or may present a jump at an unknown change-point. In these models, the logit includes a differentiable transition function that provides parametric control of the sharpness of the transition at the change-point, allowing for abrupt changes or more gradual transitions between the two different linear trends, as well as for estimation of the location of the change-point. Linear-linear logistic models are particular cases of the proposed transition models. We present a modified iteratively reweighted least squares algorithm to estimate model parameters, and we provide inference procedures including a test for the existence of the change-point. These transition models are explored in a simulation study, and they are used to evaluate the existence of a change-point in the association between plasma glucose after an oral glucose tolerance test and mortality using data from the Mortality Follow-up of the Second National Health and Nutrition Examination Survey.     

Comparison of hospital charge prediction models for gastric cancer patients: neural network vs. decision tree models

Background  

In recent years, artificial neural network is advocated in modeling complex multivariable relationships due to its ability of fault tolerance; while decision tree of data mining technique was recommended because of its richness of classification arithmetic rules and appeal of visibility. The aim of our research was to compare the performance of ANN and decision tree models in predicting hospital charges on gastric cancer patients.     

Semi‐varying coefficient multinomial logistic regression for disease progression risk prediction

This paper proposes a risk prediction model using semi‐varying coefficient multinomial logistic regression. We use a penalized local likelihood method to do the model selection and estimate both functional and constant coefficients in the selected model. The model can be used to improve predictive modelling when non‐linear interactions between predictors are present. We conduct a simulation study to assess our method's performance, and the results show that the model selection procedure works well with small average numbers of wrong‐selection or missing‐selection. We illustrate the use of our method by applying it to classify the patients with early rheumatoid arthritis at baseline into different risk groups in future disease progression. We use a leave‐one‐out cross‐validation method to assess its correct prediction rate and propose a recalibration framework to evaluate how reliable are the predicted risks. Copyright © 2016 John Wiley & Sons, Ltd.     

血清蛋白质谱结合人工神经网络在胃癌诊断中的研究

目的 建立筛选胃癌血清蛋白质谱的人工神经网络(ANN)诊断模型.方法 将84例胃癌患者和75例对照者的血清样本按照随机数字表法随机分为训练集(106例)和测试集(53例).首先应用表面加强激光解吸电离-飞行时间质谱(SELDI-TOF-MS)技术及弱阳离子交换表面芯片(CMl0)检测练集样本,结合反向传播ANN的方法建立诊断模型,进一步检测测试集样本并评价该模型的诊断价值.结果 胃癌患者与对照者血清蛋白质谱图有5个明显表达差异的蛋白质峰(P<0.05),质荷比分别为7567、6742、5262、4869、4256 m/z,5个蛋白质峰作为标志蛋白建立ANN诊断模型.利用该模型对胃癌患者进行盲法预测,结果表明其对胃癌的诊断灵敏度和特异度分别为90.0%和91.3%.结论 胃癌血清蛋白质谱结合ANN建立的诊断模型对胃癌诊断具有较高的灵敏度和特异度,可用于胃癌早期诊断与肿瘤标志物筛选研究.     

Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke.

CONTEXT: Rehospitalization following inpatient medical rehabilitation has important health and economic implications for patients who have experienced a stroke. OBJECTIVE: Compare logistic regression and neural networks in predicting rehospitalization at 3-6-month follow-up for patients with stroke discharged from medical rehabilitation. DESIGN: The study was retrospective using information from a national database representative of medical rehabilitation patients across the US. SETTING: Information submitted to the Uniform Data System for Medical Rehabilitation from 1997 and 1998 by 167 hospital and rehabilitation facilities from 40 states was examined. PARTICIPANTS: 9584 patient records were included in the sample. The mean age was 70.74 years (SD = 12.87). The sample included 51.6% females and was 77.6% non-Hispanic White with an average length of stay of 21.47 days (SD = 15.47). MAIN OUTCOME MEASURES: Hospital readmission from 80 to 180 days following discharge. Results: Statistically significant variables (P <.05) in the logistic model included sphincter control, self-care ability, age, marital status, ethnicity and length of stay. Area under the ROC curves were 0.68 and 0.74 for logistic regression and neural network analysis, respectively. The Hosmer-Lemeshow goodness-of-fit chi-square was 11.32 (df = 8, P = 0.22) for neural network analysis and 16.33 (df = 8, P = 0.11) for logistic regression. Calibration curves indicated a slightly better fit for the neural network model. CONCLUSION: There was no statistically significant or practical advantage in predicting hospital readmission using neural network analysis in comparison to logistic regression for persons who experienced a stroke and received medical rehabilitation during the period of the study.     

遗传优化的广义回归神经网络在肺结核发病预测中的应用

目的 利用西安市2008年1月至2019年10月结核病月发病率数据分别建立广义回归神经网络和BP神经网络预测模型,提出利用遗传算法的全局搜索能力优化广义回归神经的光滑因子。 方法 以2008年1月至2018年12月发病率作为训练样本,以2019年1月至10月发病率作为测试样本,对两种模型的仿真预测结果进行对比分析。 结果 遗传优化的广义回归神经网络其预测的平均绝对误差（MAE）,均方根误差（RMSE）,平均相对误差（MAPE）均小于BP神经网络,预测效果更优。 结论 遗传优化的广义回归神经网络较BP神经网络在肺结核发病率预测中有更好的拟合效果和预测精度,其预测效果更理想。其具有良好的实用价值,为肺结核发病率的预测提供了一种有效的方法。     

Empirical comparisons of proportional hazards and logistic regression models

We compare parameter estimates from the proportional hazards model, the cumulative logistic model and a new modified logistic model (referred to as the person-time logistic model), with the use of simulated data sets and with the following quantities varied: disease incidence, risk factor strength, length of follow-up, the proportion censored, non-proportional hazards, and sample size. Parameter estimates from the person-time logistic regression model closely approximated those from the Cox model when the survival time distribution was close to exponential, but could differ substantially in other situations. We found parameter estimates from the cumulative logistic model similar to those from the Cox and person-time logistic models when the disease was rare, the risk factor moderate, and censoring rates similar across the covariates. We also compare the models with analysis of a real data set that involves the relationship of age, race, sex, blood pressure, and smoking to subsequent mortality. In this example, the length of follow-up among survivors varied from 5 to 14 years and the Cox and person-time logistic approaches gave nearly identical results. The cumulative logistic results had somewhat larger p-values but were substantively similar for all but one coefficient (the age-race interaction). The latter difference reflects differential censoring rates by age, race and sex.     

Methods for interaction analyses using family-based case-control data: conditional logistic regression versus generalized estimating equations

A complex web of gene-gene and gene-environment interactions likely underlies late-onset disease development. We compared conditional logistic regression (CLR) and generalized estimating equations (GEE) in modeling such interactions in pedigrees with missing parents. Using the simulation of linkage and association (SIMLA) program, disease genes, an environmental risk factor, gene-gene interaction, and gene-environment interaction were generated in family-based data sets. Four scenarios for the relationship between the marker and disease loci were examined: linkage and association, linkage without association, association without linkage, and absence of both linkage and association. Models for CLR and GEE (with exchangeable and independence correlation matrices) were built, and type I error, power, average odds ratio (OR), standard deviation, and 95% confidence intervals were estimated. CLR and GEE were valid tests of association in the presence of linkage, but type I error was inflated for association without linkage, particularly with GEE. CLR generated estimates of the OR with lower bias but often more variability than the OR estimates observed for GEE. Further, GEE was more powerful than CLR in detecting main and interactive effects. Although GEE with both matrices had similar power, use of the independence matrix resulted in lower type I error and less biased OR estimation as compared to the exchangeable matrix. Our findings support the use of GEE in maximizing power to detect gene-gene and gene-environment interactions but caution its use under potential association without linkage (e.g., population stratification) and the interpretation of its OR estimates.     

某三甲医院神经外科手术部位感染Logistic回归与神经网络预测研究

目的应用人工神经网络及Logistic多元回归分析方法建立神经外科手术患者手术部位感染(SSI)数学预测模型。方法回顾性收集2017年1月-2017年12月于某三甲医院就诊的神经外科手术患者为研究对象,分析相关影响因素和术后感染情况,应用Logistic多元回归和人工神经网络建立神经外科手术患者SSI数学预测模型。结果共4 664例手术患者,其中有304例患者发生手术部位感染,感染发生率为6.52%;多元Logistic回归分析结果显示,患者年龄≥60岁、糖尿病、手术时间≥3h、术后再次手术、术前炎症反应、硬脑膜切开、接台手术、手术切口数是神经外科术后患者发生SSI的独立影响因素,总准确率为71.00%,ROC曲线下面积为0.833;神经网络预测SSI感染的重要性排序前5位的自变量及标准化重要性分别为患者年龄≥60岁(100%)、术前炎症反应(75.41%)、术后再次手术(66.46%)、硬脑膜切开(57.12%)、手术时间≥3h(51.86%);训练样本的准确率为91.51%,测试样本的准确率为93.24%,ROC曲线下面积为0.877。结论本研究中Logistic回归模型和神经网络模型两种预测模型均对神经外科SSI感染的预测能力较好,而神经网络模型的拟合效果相对而言更好。     

Exhaustive CHAID分类树与logistic回归在脑卒中危险因素中的应用

目的应用exhaustive CHAID分类树模型与logistic回归分析来分析北京社区居民脑卒中危险因素以及不同特征人群的重点干预因素,为加强北京市居民脑卒中的干预提供科学依据。方法于2007年6月至8月,采用整群抽样方法,对北京10 108名社区居民进行问卷调查、体格检查及检测空腹血糖、血脂。采用logistic回归与exhaustive CHAID分类树分析相结合来探讨影响北京市居民脑卒中的因素。结果 logistic回归分析和exhaustive CHAID分类树分析显示年龄、性别、踝臂指数(ABI)、高血压、腹型肥胖、高密度脂蛋白胆固醇、吸烟状况、工作强度为脑卒中的危险因素;Exhaustive CHAID分类树分析揭示老年者ABI贡献大,不容忽视中年者糖尿病。Logistic回归分析和exhaustive CHAID分类树分析的ROC曲线下面积分别为0.803和0.778,模型可靠。结论对脑卒中的防治,要在总体把握的情况下,对不同的高危人群应采取不同的防制措施。     

A feed-forward artificial neural network for prediction of the aquatic ecotoxicity of alcohol ethoxylate

A feed-forward artificial neural network (ANN) has been developed for predicting the aquatic ecotoxicity of alcohol ethoxylate (AE), a non-ionic surfactant comprising a variety of homologues. Trained with previously reported ecotoxicity data, the ANN utilizes both molecular characteristics (alkyl chain length, branching extent in alkyl chain, and ethoxylate (EO) number) and exposure features (effect endpoint, test duration, test type, and species taxon) as inputs to predict the ecotoxicity. The ANN predicted an increase in ecotoxicity for homologues with a longer or less-branched alkyl chain, or those with fewer EO units. But for long alkyl chain (>14) homologues, the ecotoxicity increase was predicted by the ANN to level off, which is obscured by existing quantitative structure-activity relationships (QSARs). A "leave-one-out" cross-validation process indicated that the prediction accuracy was within a factor of 5 with 90% probability. This research demonstrated that the current ANN covers a wider application domain with respect to the homologue range and a variety of exposure features without compromising on predictive accuracy.     

Validation data-based adjustments for outcome misclassification in logistic regression: an illustration

Misclassification of binary outcome variables is a known source of potentially serious bias when estimating adjusted odds ratios. Although researchers have described frequentist and Bayesian methods for dealing with the problem, these methods have seldom fully bridged the gap between statistical research and epidemiologic practice. In particular, there have been few real-world applications of readily grasped and computationally accessible methods that make direct use of internal validation data to adjust for differential outcome misclassification in logistic regression. In this paper, we illustrate likelihood-based methods for this purpose that can be implemented using standard statistical software. Using main study and internal validation data from the HIV Epidemiology Research Study, we demonstrate how misclassification rates can depend on the values of subject-specific covariates, and we illustrate the importance of accounting for this dependence. Simulation studies confirm the effectiveness of the maximum likelihood approach. We emphasize clear exposition of the likelihood function itself, to permit the reader to easily assimilate appended computer code that facilitates sensitivity analyses as well as the efficient handling of main/external and main/internal validation-study data. These methods are readily applicable under random cross-sectional sampling, and we discuss the extent to which the main/internal analysis remains appropriate under outcome-dependent (case-control) sampling.