检索结果-内蒙古大学图书馆

Critical Predictors for the Early Detection of Conversion From Unipolar Major Depressive Disorder to Bipolar Disorder: Nationwide Population-Based Retrospective Cohort Study

引用

JMIR MEDICAL INFORMATICS 2020年第4期8卷 e14278页

作者： Hu, Ya-Han Chen, Kuanchin Chang, I-Chiu Shen, Cheng-Che Natl Chung Cheng Univ Ctr Innovat Res Aging Soc Chiayi Cty Taiwan Natl Cheng Kung Univ MOST AI Biomed Res Ctr Tainan Taiwan Natl Cent Univ Dept Informat Management Taoyuan Taiwan Western Michigan Univ Dept Business Informat Syst Kalamazoo MI 49008 USA Natl Chung Cheng Univ Dept Informat Management Chiayi Cty Taiwan Natl Chung Cheng Univ Inst Healthcare Informat Management Chiayi Cty Taiwan Taichung Vet Gen Hosp Dept Psychiat Chiayi Branch 600Sect 2Shixian Rd Chiayi 60090 Taiwan Natl Yang Ming Univ Sch Med Taipei Taiwan

Background: Unipolar major depressive disorder (MDD) and bipolar disorder are two major mood disorders. The two disorders have different treatment strategies and prognoses. However, bipolar disorder may begin with depression and could be diagnosed as MDD in the initial stage, which may later contribute to treatment failure. Previous studies indicated that a high proportion of patients diagnosed with MDD will develop bipolar disorder over time. This kind of hidden bipolar disorder may contribute to the treatment resistance observed in patients with MDD. Objective: In this population-based study, our aim was to investigate the rate and risk factors of a diagnostic change from unipolar MDD to bipolar disorder during a 10-year follow-up. Furthermore, a risk stratification model was developed for MDD-to-bipolar disorder conversion. Methods: We conducted a retrospective cohort study involving patients who were newly diagnosed with MDD between January 1, 2000, and December 31, 2004, by using the Taiwan National Health Insurance Research Database. All patients with depression were observed until (1) diagnosis of bipolar disorder by a psychiatrist, (2) death, or (3) December 31, 2013. All patients with depression were divided into the following two groups, according to whether bipolar disorder was diagnosed during the follow-up period: converted group and nonconverted group. Six groups of variables within the first 6 months of enrollment, including personal characteristics, physical comorbidities, psychiatric comorbidities, health care usage behaviors, disorder severity, and psychotropic use, were extracted and were included in a classification and regression tree (CART) analysis to generate a risk stratification model for MDD-to-bipolar disorder conversion. Results: Our study enrolled 2820 patients with MDD. During the follow-up period, 536 patients were diagnosed with bipolar disorder (conversion rate=19.0%). The CART method identified five variables (kinds of antipsychoti

关键词： major depressive disorder bipolar disorder National Health Insurance Database data mining classification and regression tree

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Environmental and Personal Susceptibility Characteristics That Modify Genetic Risks

Evaluation of Environmental and Personal Susceptibility Char...

引用

作者： Jing Shen

Study design in understanding gene—environment interaction plays a crucial role. Different study designs with their advantages and limitations are described in this chapter. Gene penetrance has been studied in several cancers, including breast and prostate cancer. Compared with high-penetrance genes, such as breast cancer (BRCA)1, BRCA2 in breast cancer, gene—environment interaction plays a major role in cancer development where low-penetrance genes are the major players. Genetic polymorphism is determined in low- and high-penetrance genes to identify cancer-related polymorphisms. The role of genetic and epigenetic factors in cancer development is discussed. Preventive approaches, especially in the epigenetic field, show promise. A discussion about different epidemiological methods with examples is provided. less

关键词： epigenetics genetic risk Biomarker classification and regression tree environmental factors high-penetrance genes personal susceptibility

来源：评论

学校读者我要写书评

暂无评论

Feature selection based on SVM for credit scoring

Feature selection based on SVM for credit scoring

引用

2009 International Conference on Computational Intelligence and Natural Computing(CINC 2009)

作者： Ping Yao School of Economics & Management,Heilongjiang Institute of Science and Technology Harbin,150027,China

As the credit industry has been growing rapidly,huge number of consumers’ credit data are collected by the credit department of the bank and credit scoring has become a very important issue. Usually,a large amount of redundant information and features are involved in the credit dataset,which leads to lower accuracy and higher complexity of the credit scoring model,so,effective feature selection methods are necessary for credit dataset with huge number of features. This paper aims at comparing seven well-known feature selection methods for credit scoring. Which are t-test,principle component analysis (PCA),factor analysis (FA),stepwise regression,Rough Set (RS),classification and regression tree (CART) and Multivariate adaptive regression splines (MARS). Support vector machine (SVM) is used as the classification model. Two credit scoring databases are used in order to provide a reliable conclusion. Regarding the experimental results,the CART and MARS methods outperform the other methods by the overall accuracy and type I error and type II error.

关键词： credit scoring feature selection support vector machine t-test principle component analysis factor analysis stepwise regression rough set classification and regression tree multivariate adaptive regression splines

来源：评论

学校读者我要写书评

暂无评论

Real-time Prediction of Information Search Channel Using Data Mining Techniques

Real-time Prediction of Information Search Channel Using Dat...

引用

International Conference on Green Computing and Internet of Things

作者： Gaurav Khatwani Praveen Ranjan Srivastava IT Systems Indian Institute of Management

ISBN: (纸本)9781467379113

One of the biggest challenges associated with using the Internet as a real-time marketing vehicle concerns digital media fragmentation. The vast amount of potential media sources and platforms that are available to marketers entails that it can be very difficult to formulate a succinct strategy through which they can interact with the existing and potential customers. While a large number of businesses typically use consumer's previous actions as a means of understanding their information search behavior, very little is understood about how demographics influence information search and the use of various digital platforms. Previous research has focused on identifying these demographic factors but, as yet, no one has developed a real-time model that is capable of predicting consumer's information search preferences. This research considers four information search channels: personal, marketer-dominated, neutral and experiential channels, and assesses the extent to which existing classification techniques, such as classification and regression tree, neural networks and support vector machines, can be effectively employed to forecast individual's search preferences according to their demographic context. It is envisaged that the development of a method that can accurately forecast search behavior will help organizations to ensure that they allocate marketing resources in an efficient and effective manner.

关键词： Neural network Support vector machine classification and regression tree Information search channels

来源：评论

学校读者我要写书评

暂无评论

Prediction of corporate credit ratings with machine learning: Simple interpretative models

引用

FINANCE RESEARCH LETTERS 2023年 58卷

作者： Galil, Koresh Hauptman, Ami Rosenboim, Rosit Levy Ben Gurion Univ Negev Dept Econ Beer Sheva Israel Ben Gurion Univ Negev Dept Econ POB 653 IL-8410501 Beer Sheva Israel Sapir Acad Coll Dept Comp Sci Sderot Israel Sapir Acad Coll Dept Appl Econ Sderot Israel Ben Gurion Univ Negev Econ Dept Beer Sheva Israel Sapir Coll Comp Sci Dept Sderot Israel Sapir Coll Appl Econ Dept Sderot Israel

This study utilizes machine learning techniques, notably classification and regression trees (CART) and support vector regression (SVR), to predict corporate credit ratings. While SVR marginally outperforms in accuracy, CART offers interpretability. However, unconstrained models can produce non-monotonic relationships between credit ratings and core features, an undesired outcome. To circumvent this, we recommend restricted CART models that ensure interpretable, theory-consistent results. We underscore the importance of company size in credit rating prediction with an ideal model integrating size, interest coverage, and dividends. Although being a large-cap company is crucial, it doesn't guarantee high ratings, and small-cap companies rarely secure investment-grade ratings.

关键词： Corporate ratings Machine learning classification and regression tree Support Vector regression CART SVR Size

来源：评论

学校读者我要写书评

暂无评论

Movie Box Office Inteval Forecasting Based on CART

Movie Box Office Inteval Forecasting Based on CART

引用

International Symposium on Computational Intelligence and Design

作者： Zhenlong Zhang Jianping Chai Bo Li Yan Wang Min An Zhougui Deng Information Engineering School Communication University of China China Beijing China

ISBN: (纸本)9781467395885

This paper constructs a model for the forecasting of movie box office revenues during the pre-production period. Our study selects some basic variables in film forecasting field such as production country, genre, seasonality and star value. This paper divides the box office revenue into seven intervals ranged from 'flop' to 'blockbuster' and chooses classification and regression tree to predict box office in China by comparing different models. The study sets the top 100 films of 2014 in box revenues as the training set and the top 50 films of the former 5 months in 2015 as the testing set. The model produces excellent forecasting accuracy in both training and testing sets. In our model, the fitting degree of training set is 99%, and the prediction accuracy value is 76%. The importance of variables indicates that the appeal of directors and stars is notable in China.

关键词： forecast movie box office revenues intervals pre-production classification and regression tree

来源：评论

学校读者我要写书评

暂无评论

Transient Stability Assessment for Induction Generator Embedded Power Systems

Transient Stability Assessment for Induction Generator Embed...

引用

2007 IEEE Canada Electrical Power Conference (EPC 2008)

作者： Yu-Jen Lin Rui-Xiang Ho Jing-Xiong Yang Tzu-Chen Hung Meng-Jen Chen Department of Electrical Engineering I-Shou University Kaohsiung Taiwan Department of Mechanical and Automation Engineering I-Shou University Kaohsiung Taiwan Department of Electrical Engineering National Kaohsiung University of Applied Sciences Kaohsiung Taiwan

This paper presents an approach to assessing transient stability of an interconnected power system which comprises of synchronous generator (SG) and induction generator (IG). The power systems under investigated were modelled, developed and simulated using SimPowerSystems. Fundamental analysis was carried out in an attempt to discover the transient stability characters of the given power systems. Multilayer perceptrons (MLP), and classification and regression tree (CART) were employed to assess stability status and stability performance index for both SG and IG. Comprehensive digital simulations shall justify the proposed approach.

关键词： Transient Stability Assessment Induction Generator Synchronous Generator Multilayer Perceptrons classification and regression tree

来源：评论

学校读者我要写书评

暂无评论

An explainable deep-learning approach for job cycle time prediction

引用

Decision Analytics Journal 2023年 6卷

作者： Yu-Cheng Wang Toly Chen Min-Chi Chiu Department of Aeronautical Engineering Chaoyang University of Technology Taichung City Taiwan Department of Industrial Engineering and Management National Yang Ming Chiao Tung University Taiwan Department of Industrial Engineering and Management National Chin-Yi University of Technology Taichung City Taiwan

Deep neural networks (DNNs) have been applied to predict the cycle times of jobs in manufacturing accurately. However, the prediction mechanism of a DNN is complex and difficult to communicate. This limits its acceptability (or practicability) in real-world applications. An explainable deep-learning approach is proposed to solve this problem in this study. This study proposes a classification and regression tree (CART) to explain the prediction mechanism of a DNN for job cycle time prediction. The predicted value of each branch in the CART is replaced by a fuzzy linear regression (FLR) equation that estimates the cycle time range to compensate for the insufficient explainability. The explainable deep-learning approach has been applied to a real-world study from the literature to evaluate its effectiveness. According to the experimental results, the explainability of the prediction mechanism of the DNN, measured in terms of root mean squared error (RMSE), using the CART was high. In addition, the proposed methodology was able to make local explanations.

关键词： Deep learning Explainable artificial intelligence Cycle time Fuzzy linear regression classification and regression tree

来源：评论

学校读者我要写书评

暂无评论

The impact of redefining affection status for alcoholism on affected-sib-pair analysis

引用

Genetic epidemiology 1999年第S1期17 Suppl 1卷 S151-6页

作者： C S Fann Y Y Shugart H Lachman A Collins C J Chang Department of Epidemiology and Social Medicine Albert Einstein College of Medicine Bronx New York 10416 USA.

The analysis of a complex disease such as alcohol dependence requires a more precise definition of affection status. Collaborative Study on the Genetics of Alcoholism (COGA) provided a variety of qualitative and quantitative measures as well as genotype information, in addition to two criteria of affection status. To identify two groups of phenotypically "more homogeneous" individuals among alcoholics (COGA criterion), we redefined affection status by using cluster analysis and classification and regression tree, incorporating some important covariates such as event related potentials, monoamine oxidase B activity, status of smoking, age of onset, three variables of personality assessed with the Tridimensional Personality Questionnaire and three latent class variables. With redefined affection status, we repeated nonparametric analysis by three sib pair analysis programs (SIBPAL, SIBPAIR, and BETA) using nine candidate DNA markers identified by Reich et al. [1998] and Long et al. [1998]. The goals of our analysis are 1) to confirm previous results for these nine markers with redefined affection status and 2) to compare the performance from these three programs.

关键词： classification and regression tree cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Identifying type 1 and type 2 diabetic cases using administrative data: a tree-structured model

引用

Journal of diabetes science and technology 2011年第3期5卷 486-93页

作者： Weihsuan Lo-Ciganic Janice C Zgibor Kristine Ruppert Vincent C Arena Roslyn A Stone Department of Epidemiology Graduate School of Public Health University of Pittsburgh Pittsburgh Pennsylvania USA. wel32@pitt.edu

BACKGROUND:To date, few administrative diabetes mellitus (DM) registries have distinguished type 1 diabetes mellitus (T1DM) from type 2 diabetes mellitus (T2DM). OBJECTIVE:Using a classification tree model, a prediction rule was developed to distinguish T1DM from T2DM in a large administrative database. METHODS:The Medical Archival Retrieval System at the University of Pittsburgh Medical Center included administrative and clinical data from January 1, 2000, through September 30, 2009, for 209,647 DM patients aged ≥18 years. Probable cases (8,173 T1DM and 125,111 T2DM) were identified by applying clinical criteria to administrative data. Nonparametric classification tree models were fit using TIBCO Spotfire S+ 8.1 (TIBCO Software), with model size based on 10-fold cross validation. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of T1DM were estimated. RESULTS:The main predictors that distinguished T1DM from T2DM are age <40 years; International classification of Disease, 9th revision, codes of T1DM or T2DM diagnosis; inpatient oral hypoglycemic agent use; inpatient insulin use; and episode(s) of diabetic ketoacidosis diagnosis. Compared with a complex clinical algorithm, the tree-structured model to predict T1DM had 92.8% sensitivity, 99.3% specificity, 89.5% PPV, and 99.5% NPV. CONCLUSION:The preliminary predictive rule appears to be promising. Being able to distinguish between DM subtypes in administrative databases will allow large-scale subtype-specific analyses of medical care costs, morbidity, and mortality.

关键词： administrative database classification and regression tree diabetes Medical Archival Retrieval System negative predictive value positive predictive value sensitivity specificity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：