A two-phase hybrid approach using feature selection and Adaptive SVM for chronic disease classification

Abstract

Chronic diseases represent a major health burden worldwide. Machine learning techniques have been extensively used in the medical field to diagnose chronic diseases. In this research, a fast, novel adaptive classification system is presented for the diagnosis of chronic diseases. For this purpose, the proposed approach employs a hybrid approach comprising of PCA and ReliefF method with optimized Support Vector Machine classifier. To attain high classification accuracy, comprehensibility, and consistency, efficient parameter optimization approach is applied for the SVM classifier. To evaluate the system’s performance, nine well-known disease datasets are used for medical diagnosis. The resulted system is capable to adapt any kind of dataset and shows outstanding results in terms of accurate classification with the significant reduction of dimension and computational complexity. Moreover, the system exhibits higher accuracy when compared to classical SVM and Adaptive SVM without feature selection technique.

KEYWORDS:

• Chronic diseases
• adaptive support vector machine
• hybrid feature selection
• disease diagnosis
• parameter optimization

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Divya Jain

Mrs Divya is an active and dedicated resource in the Computer Science Department. She is currently working as a University Fellow in the Computer Science Department from 2015. She did her graduation in B.Tech Computer Science and Engineering with distinction from Maharishi Dayanand, University, Rohtak in 2012 and M.Tech in Computer science and Engineering in 2014 from ITM university, Gurugram. She did Diploma in .NET Technologies from NIIT Ltd. She is currently pursuing Ph.D. from NCU, Gurugram in the field of data mining and machine learning. She has published one book and many research papers in reputed International Journals and Conferences. Her core subjects are Data Mining and Machine Learning.

Vijendra Singh

Vijendra Singh received his Ph.D. degree in Engineering and M.Tech degree in Computer Science and Engineering from Birla Institute of Technology, Mesra, Ranchi. He has 19 years of experience in research and teaching including IT industry. Dr Singh major research concentration has been in the areas of Data Mining, Pattern Recognition, Image Processing, Big Data, Machine Learning and Soft Computation. He has more than 50 scientific papers in this domain. He was the project team member of Order Routing and Risk Management System for stock exchange, Bombay, India. He received IBM Edu Leader Award. Singh Vijendra is a member of ISTE, IEEE, and ACM.

He has programme committee member of 30 IEEE conferences and word reputed international conferences. Singh Vijendra served as Associate Editor, International Journal of Healthcare Information Systems and Informatics, IGI Global, USA; Guest Editor special issue on ‘Data Mining and Decision Sciences in Engineering,’ International Journal of Healthcare Information Systems and Informatics, IGI Global, USA; Editorial Board Members, International Journal of Information and Decision Sciences, Inderscience, Switzerland; Editor in Chief, International Journal of Social Computing and Cyber-Physical Systems, Inderscience, UK; Editorial Board Members, International Journal of Multivariate Data Analysis, Inderscience, UK; Editorial Board Members, International Journal of Internet of Things and Cyber-Assurance, Inderscience, UK.