Litcius/Paper detail

Multistage feature selection and stacked generalization model for cancer detection

Sulekha Das, Avijit Kumar Chaudhuri, Sayak Das, Partha Ghosh

2025Scientific Reports6 citationsDOIOpen Access PDF

Abstract

To address the issue of reliable cancer screening, this study proposes a novel approach to select key features in conjunction with a stacking classifier. It reduces the number of features required while maintaining the same diagnostic accuracy. The experimental results demonstrate that the proposed method yields superior performance in terms of accuracy, sensitivity, precision, specificity, and AUC on each benchmark dataset. This stacked model, built from Logistic Regression, Naïve Bayes, Decision Tree and a Multilayer Perceptron as meta-classifier, achieves 100% accuracy, sensitivity, specificity and AUC using the selected optimal feature subsets. The findings confirm that intelligent feature selection helps models perform better and is easier to use in identification of cancer.

Topics & Concepts

Computer scienceBenchmark (surveying)Feature selectionArtificial intelligenceGeneralizationFeature (linguistics)Decision treePattern recognition (psychology)Key (lock)Identification (biology)Selection (genetic algorithm)Data miningMachine learningStackingMultilayer perceptronPerceptronTree (set theory)Feature extractionMedical diagnosisLogistic model treeCancer detectionDecision tree modelInformation gainModel selectionClassifier (UML)Random forestCancerTree structureAI in cancer detectionBrain Tumor Detection and ClassificationArtificial Intelligence in Healthcare