Abstract
The field of data analytics dealt with various methods to analyze the available data and help us to drawn into a point of conclusion about that information. Machine will learn the behavior based on the algorithms applied on those data and provide an appropriate conclusion. When these kinds of data analytic metrics applied to medical diagnosis various symptoms obtained from the patients and then the disease could be detected effectively. When certain optimization methods are applied on the data, the overall efficiency of the system will be improved considerably. To meet the challenges in diagnosing breast cancer based on clinical record sources, different symptoms in descriptions, clinical symptoms, a novel method, which consists of choosing the suitable features, multi-class functions, and multi-label parameters, has been proposed. The proposed work will be implemented as two steps such as discriminative symptoms selection and multi-syndrome learning. Public Breast Cancer Wisconsin (Diagnostic) Data Set has been taken for implementation. The breast cancer data set utilized for this work comprises 699 tumour samples. In that 458(65.5 %) samples belong to Benevolent (non-cancer) tumours and 241(34.5%) belongs to malevolent(cancer) tumours. The overall verisimilitude is 95.23% which will be improved to a greater extent when compared to the existing schemes.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.