Vol.:(0123456789) 1 3 Evolutionary Intelligence https://doi.org/10.1007/s12065-019-00327-1 SPECIAL ISSUE Hybrid genetic algorithm and a fuzzy logic classifer for heart disease diagnosis G. Thippa Reddy 1  · M. Praveen Kumar Reddy 1  · Kuruva Lakshmanna 1  · Dharmendra Singh Rajput 1  · Rajesh Kaluri 1  · Gautam Srivastava 2,3 Received: 11 September 2019 / Revised: 11 November 2019 / Accepted: 15 November 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019 Abstract For the past two decades, most of the people from developing countries are sufering from heart disease. Diagnosing these diseases at earlier stages helps patients reduce the risk of death and also in reducing the cost of treatment. The objective of adaptive genetic algorithm with fuzzy logic (AGAFL) model is to predict heart disease which will help medical practitioners in diagnosing heart disease at early stages. The model consists of the rough sets based heart disease feature selection module and the fuzzy rule based classifcation module. The generated rules from fuzzy classifers are optimized by applying the adap- tive genetic algorithm. First, important features which efect heart disease are selected by rough set theory. The second step predicts the heart disease using the hybrid AGAFL classifer. The experimentation is performed on the publicly available UCI heart disease datasets. Thorough experimental analysis shows that our approach has outperformed current existing methods. Keywords Disease classifcation · Adaptive genetic algorithm · Rough set theory · Feature reduction · Membership function 1 Introduction The progress made in the feld of computer technology, storage of digital data, and technological advancement in communication technologies has enabled the generation of huge amounts of data in the medical feld [29]. Extracting patterns from medical data helps medical practitioners in diagnosing patients. A patient’s data is comprised of attributes like demogra- phy, test results, images, video clippings, and others [12]. Extraction of desired information from the voluminous data manually is a herculean task considering size of the data and wide dimensionsality of the data [2]. Hence, automated analyzing techniques are required for analyzing the data. It is handy to use data mining techniques which can auto- mate the analysis as well as handle the large datasets [1]. Data mining [3] helps doctors in diagnosing the patients by extracting useful knowledge from patients’ medical data [6, 16, 18]. We can use the term Medical data mining for mod- els classifying medical data. It uses data mining methods for obtaining accurate information. Medical data mining is used to diagnose illness, administer therapy, establish rap- port among doctors as well as patients, bettering managing of healthcare, and so on [15, 24]. Every day, gigabytes of medical data is generated from several sources including image databases like SPECT, MRI, PET, signal databases like ECG and EEG [25]. Unlike traditional data mining, data mining in the medical feld is very cumbersome [5, 12, 27]. * Gautam Srivastava srivastavag@brandonu.ca G. Thippa Reddy thippareddy.g@vit.ac.in M. Praveen Kumar Reddy praveenkumarreddy@vit.ac.in Kuruva Lakshmanna lakshman.kuruva@vit.ac.in Dharmendra Singh Rajput dharmendrasingh@vit.ac.in Rajesh Kaluri rajesh.kulari@vit.ac.in 1 Vellore Institute of Technology, Vellore, Tamil Nadu, India 2 Department of Mathematics and Computer Science, Brandon University, Brandon R7A 6A9, Canada 3 Research Center for Interneural Computing, China Medical University, Taichung 40402, Taiwan, ROC