Fisher score and Matthews correlation coefficient-based feature subset selection for heart disease diagnosis using support vector machines

Saqlain, Syed Muhammad; Sher, Muhammad; Shah, Faheem; Khan, Imran; Ashraf, Muhammad Usman; Awais, Muhammad; Ghani, Anwar

doi:10.1007/s10115-018-1185-y

Cited by 97 publications

(27 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, first, the data were reduced to a dimensional scale, and then, with the help of a support vector machine with a radial base neural network kernel, a classification model was presented. And reached 81.19 percent accuracy for test data [6].…”

Section: Introductionmentioning

confidence: 90%

Combining Random Forest and Neural Networks Algorithms to Diagnose Heart Disease

Dehnavi¹,

Emamipour²,

Golabpour

2020

Front Health Inform

View full text Add to dashboard Cite

Introduction: Heart disease is known as one of the most important causes of death in today's society and so far no definitive method has been found to predict it and several factors are effective in contracting this disease. Therefore, the aim of this study was to provide a data mining model for predicting heart disease.Material and Methods: This study used standard data from UCI. These data include four Cleveland, Hungarian, Swiss and Long Beach VA databases. These data include 13 independent variables and one dependent variable. The data are missing, and the EM algorithm was used to control this loss, and at the end of the data, a suggestion algorithm was implemented that combined the two random forest algorithms and the artificial neural network.Results: In this study, data was divided into two training sets and 10-Fold method was used. To evaluate the algorithms, three indicators of sensitivity, specificity, accuracy were used and the accuracy of the prediction algorithm for four data Cleveland, Hungarian, Switzerland and Long Beach VA reached 87.65%, 94.37%, 93.45% and 85%, respectively. Then, the proposed algorithm was compared with similar articles in this field, and it was found that this algorithm is more accurate than similar methods.Conclusion: The results of this study showed that by combining the two algorithms of random forest and artificial neural network, a suitable model for predicting heart attacks can be provided.

show abstract

Section: Introductionmentioning

confidence: 90%

Combining Random Forest and Neural Networks Algorithms to Diagnose Heart Disease

Dehnavi¹,

Emamipour²,

Golabpour

2020

Front Health Inform

View full text Add to dashboard Cite

show abstract

“…(i) Filter methods: These techniques look for the relationships among features and investigate how much information exists in a feature. For this purpose, various mathematical formulas have been proposed, including Entropy 18 , mutual information 19 , Fisher score 20 , correlation 21 , Laplacian 22 , etc. Although these approaches are simple and have a low time-complexity, their performance is lower than the other categories 23 .…”

Section: Related Workmentioning

confidence: 99%

A machine learning method based on the genetic and world competitive contests algorithms for selecting genes or features in biological applications

Masoudi-Sobhanzadeh

MotieGhader

Omidi

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Gene/feature selection is an essential preprocessing step for creating models using machine learning techniques. It also plays a critical role in different biological applications such as the identification of biomarkers. Although many feature/gene selection algorithms and methods have been introduced, they may suffer from problems such as parameter tuning or low level of performance. To tackle such limitations, in this study, a universal wrapper approach is introduced based on our introduced optimization algorithm and the genetic algorithm (GA). In the proposed approach, candidate solutions have variable lengths, and a support vector machine scores them. To show the usefulness of the method, thirteen classification and regression-based datasets with different properties were chosen from various biological scopes, including drug discovery, cancer diagnostics, clinical applications, etc. Our findings confirmed that the proposed method outperforms most of the other currently used approaches and can also free the users from difficulties related to the tuning of various parameters. As a result, users may optimize their biological applications such as obtaining a biomarker diagnostic kit with the minimum number of genes and maximum separability power.

show abstract

“…Accuracy (ACC), sensitivity (SENS), specificity (SPEC), precision (PREC), F1-measure (F1), Receiver Operator Characteristic Curve (ROC), and Matthews Correlation Coefficient (MCC) were demonstrated. For a detailed explanation of the metrics please refer to the following articles, which also demonstrate the advantages of MCC metric when dealing with classification models [20,[41][42][43].…”

Section: Data Pre-processing and Validationmentioning

confidence: 99%

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

Furxhi¹,

Murphy²

2020

IJMS

View full text Add to dashboard Cite

The practice of non-testing approaches in nanoparticles hazard assessment is necessary to identify and classify potential risks in a cost effective and timely manner. Machine learning techniques have been applied in the field of nanotoxicology with encouraging results. A neurotoxicity classification model for diverse nanoparticles is presented in this study. A data set created from multiple literature sources consisting of nanoparticles physicochemical properties, exposure conditions and in vitro characteristics is compiled to predict cell viability. Pre-processing techniques were applied such as normalization methods and two supervised instance methods, a synthetic minority over-sampling technique to address biased predictions and production of subsamples via bootstrapping. The classification model was developed using random forest and goodness-of-fit with additional robustness and predictability metrics were used to evaluate the performance. Information gain analysis identified the exposure dose and duration, toxicological assay, cell type, and zeta potential as the five most important attributes to predict neurotoxicity in vitro. This is the first tissue-specific machine learning tool for neurotoxicity prediction caused by nanoparticles in in vitro systems. The model performs better than non-tissue specific models.

show abstract

Fisher score and Matthews correlation coefficient-based feature subset selection for heart disease diagnosis using support vector machines

Cited by 97 publications

References 23 publications

Combining Random Forest and Neural Networks Algorithms to Diagnose Heart Disease

Combining Random Forest and Neural Networks Algorithms to Diagnose Heart Disease

A machine learning method based on the genetic and world competitive contests algorithms for selecting genes or features in biological applications

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

Contact Info

Product

Resources

About