Interactive Knowledge Discovery for Temporal Lobe Epilepsy

Ghannad-Rezaie, Mostafa; Soltanian‐Zadeh, Hamid

doi:10.5772/6411

Cited by 4 publications

(2 citation statements)

References 28 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is imperative for a healthcare industry to perform in-depth analysis of massive medical data in making operational or strategic decisions. Among examples of the medical or clinical data includes the breast cancer [3], heart and coronary diseases [4,5], liver cancer [6], diabetes [7], Parkinson's disease [8,9], and epilepsy [10]. Specific to the Chronic Kidney Disease (CKD) classification and prediction, other data mining algorithms that have been used are the multilayer perceptron, radial basis functions network and logistic regression [11,12], decision forest [13], time-series analysis [14], naive Bayes and artificial neural networks [15].…”

Section: Introductionmentioning

confidence: 99%

Comparative analysis of classification algorithms for chronic kidney disease diagnosis

Saringat¹,

Saedudin²,

Samsudin³

2019

Bulletin EEI

View full text Add to dashboard Cite

Chronic Kidney Disease (CKD) is one of the leading cause of death contributed by other illnesses such as diabetes, hypertension, lupus, anemia or weak bones that lead to bone fractures. Early prediction of CKD is important in order to contain the disesase. However, instead of predicting the severity of CKD, the objective of this paper is to predict the diagnosis of CKD based on the symptoms or attributes observed in a particular case, whether the stage is acute or chronic. To achieve this, a classification model is proposed to label stage of severity for kidney diseases patients. The experiments then investigated the performance of the proposed classification model based on eight supervised classification algorithms, which are ZeroR, Rule Induction, Support Vector Machine, Naïve Bayes, Decision Tree, Decision Stump, k-Nearest Neighbour, and Classification via Regression. The performance of the all classifiers is evaluated based on accuracy, precision, and recall. The results showed that the regression classifier perform best in the kidney diagnostic procedure.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparative analysis of classification algorithms for chronic kidney disease diagnosis

Saringat¹,

Saedudin²,

Samsudin³

2019

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…Mostafa GhannadRezaie et al [2] developed a system, allows to interact with the data mining procedure. Provides a place to manually generate generatedrules.…”

Section: Related Workmentioning

confidence: 99%

Data Mining Techniques to Predict Chronic Kidney Disease and its Stages

Nisarga¹,

Kanchana²

2018

IJET

View full text Add to dashboard Cite

Chronic Kidney Disease incorporates the state where the kidneys fail to function and reduce the potential to keep a person suffering from the disease healthy. When the condition of the kidneys gets worse, the wastes in the blood are formed in high level. Data mining has been a present pattern for accomplishing analytic outcomes. Colossal measure of un-mined data is gathered by the human services industry so as to find concealed data for powerful analysis and basic leadership. Data mining is the way towards extricating concealed data from gigantic datasets. The goal of our paper is to anticipate CKD utilizing the classification strategy Naïve Bayes. The phases of CKD are anticipated in the light of Glomerular Filtration Rate (GFR).

show abstract

Selection–fusion approach for classification of datasets with missing values

Ghannad-Rezaie

Soltanian-Zadeh

Ying

et al. 2010

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

This paper proposes a new approach based on missing value pattern discovery for classifying incomplete data. This approach is particularly designed for classification of datasets with a small number of samples and a high percentage of missing values where available missing value treatment approaches do not usually work well. Based on the pattern of the missing values, the proposed approach finds subsets of samples for which most of the features are available and trains a classifier for each subset. Then, it combines the outputs of the classifiers. Subset selection is translated into a clustering problem, allowing derivation of a mathematical framework for it. A trade off is established between the computational complexity (number of subsets) and the accuracy of the overall classifier. To deal with this trade off, a numerical criterion is proposed for the prediction of the overall performance. The proposed method is applied to seven datasets from the popular University of California, Irvine data mining archive and an epilepsy dataset from Henry Ford Hospital, Detroit, Michigan (total of eight datasets). Experimental results show that classification accuracy of the proposed method is superior to those of the widely used multiple imputations method and four other methods. They also show that the level of superiority depends on the pattern and percentage of missing values.

show abstract

Interactive Knowledge Discovery for Temporal Lobe Epilepsy

Cited by 4 publications

References 28 publications

Comparative analysis of classification algorithms for chronic kidney disease diagnosis

Comparative analysis of classification algorithms for chronic kidney disease diagnosis

Data Mining Techniques to Predict Chronic Kidney Disease and its Stages

Selection–fusion approach for classification of datasets with missing values

Contact Info

Product

Resources

About