Feature Selection Using Improved Teaching Learning Based Algorithm on Chronic Kidney Disease Dataset

Manonmani, M.; Sarojini, B.

doi:10.1016/j.procs.2020.04.178

Cited by 22 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TLBO-SSA shows a good performance. Also, an Improved TLBO (ITLBO) algorithm has been proposed to solve the feature selection for early diagnosis of chronic diseases [31]. The ITLBO algorithm outperforms the basic TLBO in terms of the selected feature's size on an applied chronic kidney disease dataset.…”

Section: A Related Work On Feature Selection Approaches Based On Meta...mentioning

confidence: 99%

“…Therefore, we review some relevant works on binary TLBO algorithms in this subsection. Several variants of the binary TLBO algorithm have been proposed [31], [32], [33], [43] to address binary optimization problems. The most common and efficient approaches to convert the continuous TLBO optimization algorithm to its binary version rely on transfer functions or genetic-operator-based binarization techniques [46].…”

Section: B Related Work On Binary Tlbo Algorithmsmentioning

confidence: 99%

“…Therefore, TLBO has been widely applied, adapted, extended, and hybridized with other swarm and intelligent evolutionary algorithms to solve many continuous and discrete optimization problems [30]. However, there are very few TLBO-based approaches for the feature selection problem in medical diagnosis, such as the hybrid TLBO with the Salp Swarm Algorithm (TLBO-SSA) [13], the Improved TLBO (ITLBO) algorithm [31], the Multi-objectives Binary TLBO (MBTLBO) [32], and the New Modified Binary Teaching-Learning-Based Optimization (NMBTLBO) [33]. Generally, these algorithms look into an excellent global search ability and fast convergence to maximize the intelligent system to generate feature subsets with improved diagnostic performance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wrapper-Based Feature Selection for Medical Diagnosis: The BTLBO-KNN Algorithm

et al. 2023

View full text Add to dashboard Cite

Medical diagnosis research has recently focused on feature selection techniques due to the availability of multiple variables in medical datasets. Wrapper-based feature selection approaches have shown promise in providing faster and more cost-effective predictors. However, selecting the most relevant features from medical datasets to increase disease classification accuracy remains a challenging research issue. To address this challenge, we propose an effective wrapper-based feature selection approach called BTLBO-KNN. It combines an improved Binary Teaching-Learning Based Optimization (BTLBO) algorithm with the K-Nearest Neighbor (KNN) classifier to accelerate the convergence rate in finding the near-optimal features subset. BTLBO-KNN incorporates two new efficient binary teaching and learning processes, an abandoned learner's replacement mechanism, and a teacher knowledge improvement method. We extensively compare BTLBO-KNN with recent state-of-the-art wrapper-based feature selection approaches on COVID-19 and 23 gene-expression and medical datasets with different dimensional complexities. Our results demonstrate the superiority of BTLBO-KNN over its alternatives in terms of minimizing the number of selected features and the classification error rate.

show abstract

Section: A Related Work On Feature Selection Approaches Based On Meta...mentioning

confidence: 99%

Section: B Related Work On Binary Tlbo Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wrapper-Based Feature Selection for Medical Diagnosis: The BTLBO-KNN Algorithm

et al. 2023

View full text Add to dashboard Cite

show abstract

“…On the same dataset, Salekin et al obtained a F1 score using a Random Forest Classifier (RFC) and also showed that a close result ( F1 score) can be obtained using only ten relevant predictive attributes 14 . Manonmani et al used the Improved Teacher Learner Based Optimization (ITLBO) algorithm as an FS technique that provided them with features out of and obtained an accuracy of using the Convolutional Neural Network (CNN) classification algorithm 15 . Rubini et al used Fruit Fly Optimization Algorithm (FFOA) as an FS technique that resulted in relative attributes out of and obtained accuracy using Multi-Kernel Support Vector Machine (MKSVM) as the classifier 16 .…”

Section: Introductionmentioning

confidence: 99%

“…A comparison between GA, PSO, and BBO in finding an optimal feature set from Clusters of microcalcifications (MCC) conducted by Khehra et al demonstrates that BBO performance is marginally superior to the other two 35 , 48 . In a CKD dataset, Manonmani et al utilized the ITLBO method to find the best feature subset, and it chose 16 out of 24 features as the best feature subset 15 . The Correlation-based Feature Selection (CFS) approach was employed by Wibawa et al on the same CKD dataset to identify the best features.…”

Section: Introductionmentioning

confidence: 99%

Detection of the chronic kidney disease using XGBoost classifier and explaining the influence of the attributes on the model using SHAP

Raihan

Khan

Kee

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Chronic kidney disease (CKD) is a condition distinguished by structural and functional changes to the kidney over time. Studies show that 10% of adults worldwide are affected by some kind of CKD, resulting in 1.2 million deaths. Recently, CKD has emerged as a leading cause of mortality worldwide, making it necessary to develop a Computer-Aided Diagnostic (CAD) system to diagnose CKD automatically. Machine Learning (ML) based CAD system can be used by a clinician to automatically diagnoses mass people. Since ML models are considered a black box, it is also necessary to expose influential causes behind a model's prediction of a particular output. So that, a doctor can make a more rational decision based on the model's output and analysis of the features influence on the model. In this paper, we have used the XGBoost as the ML classifier to predict whether a patient has CKD or not. Using the XGBoost classifier, we have obtained an accuracy, precision, recall, and F1 score of $$99.16{\%}, 100{\%}, 98.68{\%},$$ 99.16 % , 100 % , 98.68 % , and $$99.33{\%},$$ 99.33 % , respectively using all $$24$$ 24 features. Furthermore, we have used Biogeography Based Optimization (BBO) algorithm to find an effective subset of the features. The BBO algorithm selected almost half of the initial features. We have obtained an accuracy, precision, recall, and F1 score of $$98.33{\%}, 100{\%}, 97.36{\%},$$ 98.33 % , 100 % , 97.36 % , and $$98.67{\%},$$ 98.67 % , respectively using only 13 features selected by the BBO algorithm. Finally, we have explained the impact of the feature on the ML models using the SHapley Additive exPlanations (SHAP) analysis. Using SHAP analysis and BBO algorithm, we have found that hemoglobin and albumin mostly contribute to the detection of CKD.

show abstract

Fuzzy Neural Networks for Detection Kidney Diseases

Abiyev¹,

Idoko²,

Dara³

2021

Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation

View full text Add to dashboard Cite

This study presents a learning mode-base Fuzzy Neural Networks (FNN) to detect chronic kidney disease (CKD). Combining the fuzzy set theory with the NN structure helps the proposed system to learn sensor data and adjust network parameters. The structure and algorithms of multi-input multi-output FNN are presented. The FNN algorithms implement the TSK type fuzzy rules. The learning of the system is executed by utilizing a gradient descent algorithm and c-means clustering. The presented system is trained using kidney datasets. The performance of the system is evaluated using mean accuracy, sensitivity, specificity and precision which were obtained as 99.75%, 100%, 99.34% and 99.9% correspondingly. The comparison of the results of simulation of the proposed model with the results of other existing algorithms demonstrates the efficiency of the presented FNN model. The experimental results indicate that the approach proposed offers reasonable accuracy of detection and has the potential to be applied in clinical practice.

show abstract

Feature Selection Using Improved Teaching Learning Based Algorithm on Chronic Kidney Disease Dataset

Cited by 22 publications

References 20 publications

Wrapper-Based Feature Selection for Medical Diagnosis: The BTLBO-KNN Algorithm

Wrapper-Based Feature Selection for Medical Diagnosis: The BTLBO-KNN Algorithm

Detection of the chronic kidney disease using XGBoost classifier and explaining the influence of the attributes on the model using SHAP

Fuzzy Neural Networks for Detection Kidney Diseases

Contact Info

Product

Resources

About