Comparative Evaluation of the Different Data Mining Techniques Used for the Medical Database

Kasperczuk, Anna; Dardzińska, Agnieszka

doi:10.1515/ama-2016-0036

Cited by 20 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to test the accuracy of the constructed model, a matrix of errors (Table 1) was used to calculate the measures describing the correctness of the classification [24,25].…”

Section: Model Testingmentioning

confidence: 99%

Smart Model to Distinguish Crohn’s Disease from Ulcerative Colitis

2019

Self Cite

View full text Add to dashboard Cite

Inflammatory bowel diseases (IBD) is a term referring to chronic and recurrent gastrointestinal disease. It includes Crohn’s disease (CD) and ulcerative colitis (UC). It is undeniable that presenting features may be unclear and do not enable differentiation between disease types. Therefore, additional information, obtained during the analysis, can definitely provide a potential way to differentiate between UC and CD. For that reason, finding the optimal logistic model for further analysis of collected medical data, is a main factor determining the further precisely defined decision class for each examined patient. In our study, 152 patients with CD or UC were included. The collected data concerned not only biochemical parameters of blood but also very subjective information, such as data from interviews. The built-in logistics model with very high precision was able to assign patients to the appropriate group (sensitivity = 0.84, specificity = 0.74, AUC = 0.93). This model indicates factors differentiating between CD and UC and indicated odds ratios calculated for significantly different variables in these two groups. All obtained parameters of the model were checked for statistically significant. The constructed model was able to be distinguish between ulcerative colitis and Crohn’s disease.

show abstract

“…In order to test the accuracy of the constructed model, a matrix of errors (Table 1) was used to calculate the measures describing the correctness of the classification [24,25].…”

Section: Model Testingmentioning

confidence: 99%

Smart Model to Distinguish Crohn’s Disease from Ulcerative Colitis

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…It implements data mining algorithms using a java language and supports several standard data mining tasks, more specifically, data pre-processing, clustering, classification, regression, visualization, and feature selection. There are many advantages of it such as 1) It is fully implemented in the Java programming language, therefore it runs on almost any architecture; 2) it is easy to use due to its graphical user interface; 3) It has a huge collection of data preprocessing and modelling techniques [44,45]. It supports multiple dataset format like csv data files, Json Instance files, libsvm data files, Matlab ASCII files etc., with the default being ARFF.…”

Section: Wekamentioning

confidence: 99%

Data Level Approach for Multiclass Imbalance Financial Data

Ruzgar

Chua

2020

Wseas Transactions on Computers

View full text Add to dashboard Cite

In the real world, the class imbalance problem is a common issue in which classifier gives more importance to the majority class whereas less importance to the minority class. In class imbalance, imbalance metrics would not be suitable to evaluate the performance of classifiers with error rate or predictive accuracy. One type of imbalance data -handling method is resampling. In this paper, three resampling methods, oversampling, under-sampling and hybrid, methods are used with different approaches for in class imbalance of two different financial data to see the impact of class imbalance ratios on performance measures of nine different classification algorithms. Aiming to achieve better change classification performance, the performance of the classification algorithms, Bayes Net, Navie Bayes, J48, Random Forest Meta-Attribute Selected Classifier, MetaClassification via Regression, Meta-Logitboost, Logistic Regression, and Decision Tree, are measured on two Canadian Banks multiclass imbalance data with the performance measures, Precision, Recall, ROC Area and Kappa Statistic, by using WEKA software. The outcome of these performance measurements compared with three different resampling methods. The results provide us with a clear picture on the overall impact of class imbalance on the classification dataset and they indicate that proposed resampling methods can also be used for in class imbalance problems

show abstract

“…Undoubtedly, it will deepen current knowledge about UC as well as CD. Answers to many bothering doctors may bring methods of knowledge exploration from databases [10][11][12][13][14][15]. For this reason, the methods of data mining in combination with statistical methods in the analysis of medical data of patients covered by the disorder were used in the work.…”

Section: Article Info Abstractmentioning

confidence: 99%

Differentiating Crohn’s Disease from Ulcerative Colitis - New Factors

Kasperczuk

Dardzińska

2019

BJSTR

Self Cite

View full text Add to dashboard Cite

Crohn's disease (CD) and ulcerative colitis (UC) have been known to physicians for decades. Unfortunately, so far there are many unknowns regarding CD and UC. There are numerous descriptions of clinical cases, different locations of disease symptoms, and descriptions of symptoms located both in the gastrointestinal tract and symptoms accompanying the disease.All this information sheds light on the etiology of inflammatory bowel disease (IBD) do not completely resolve their complexity. An analysis of the literature presented in the work indicates that the characteristics of diseases are often unambiguous. This contributes to the fact that IBD diagnostics are often difficult and create many problems [1][2][3]. Despite many years of research on inflammatory bowel diseases, they are still of interest to scientists today. Nonspecific inflammatory bowel disease is a term referring to chronic and recurrent gastrointestinal disease. A number of clinical symptoms distinguish between CD and UC, whose clinical picture is relatively diverse. However, in many cases the diagnosis is not straightforward, which contributes to the interest of researchers worldwide in the disorders under discussion. The inflammatory changes in the course of UC are continuous and limited to the mucous membrane of the large intestine. UC-related inflammation usually involves the mucosa and submucosa usually begins in the rectum and spread proximal to the colon. The affected tissue is swollen, with the presence of erosions and ulcers, which lead to spontaneous bleeding.In most cases, UC initially occurs smoothly, with worsening symptoms within a few weeks. It happens, however, that the disease begins suddenly and goes very quickly. In such cases, due to the lack of the effect of conservative treatment, surgical treatment is already implemented in the early stages of the disease. However, in most cases, after the first shot of the disease, it goes into remission, after which it becomes more severe again. Such continuous conditions of illness and remission may last even several dozen years [1,2]. In the case of CD, the condition most often includes the small intestine and caecum, which accounts for 40% of cases, only small intestine (30% of patients) and only large intestine (25% of cases). In situations where only the large intestine is covered, two forms of the disease are recognized. The first one concerns about two thirds of cases and consists in taking the entire length of the large intestine with the disease state, while the second involves the occurrence of staple

show abstract

Comparative Evaluation of the Different Data Mining Techniques Used for the Medical Database

Cited by 20 publications

References 10 publications

Smart Model to Distinguish Crohn’s Disease from Ulcerative Colitis

Smart Model to Distinguish Crohn’s Disease from Ulcerative Colitis

Data Level Approach for Multiclass Imbalance Financial Data

Differentiating Crohn’s Disease from Ulcerative Colitis - New Factors

Contact Info

Product

Resources

About