ITM Web Conf.
Volume 44, 2022International Conference on Automation, Computing and Communication 2022 (ICACC-2022)
|Number of page(s)||6|
|Published online||05 May 2022|
Diabetes & Heart Disease Prediction Using Machine Learning
Ramrao Adik Institute of Technology, D Y Patil Deemed to be University, Navi Mumbai, India
One of the root causes of mortality in today's world is the culmination of several heart disease and diabetes illnesses. In clinical data analysis, predicting multiple diseases is a significant challenge. The machine learning approach has proved to be functional in assisting in the decision-making and governing of large amounts of data generated by the healthcare field. The various experiments scratch the surface of machine learning to predict different diseases. The papers present a novel method for identifying significant features using machine learning techniques, which improves the diagnosis of multi-purpose disease prediction. The different features and many well-known classification methods are used to implement the prediction model to predict the heart disease and diabetes. The proposed method utilizes ensemble approach for achieving a higher degree of accuracy rates for by using classification algorithms and feature selection methods. The proposed method implements voting classifier that has sigmoid SVC, AdaBoost, and Decision tree algorithms. The paper also implements the traditional classifiers and presents the comparison of different models in terms of accuracy. The web application is also developed for users to avail its services very easily and make it convenient for their use, particularly in the prediction of heart and diabetes collectively.
Key words: Machine Learning / classification / feature selection / prediction / heart disease / diabetes
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.