Machine Learning for Accurate Prediction of Cardiac Arrhythmia
Rashmitha H.R1, Sumana M2
1Rashmitha H.R*, M.Tech, Software Engineering, M S Ramaiah Institute of Technology (MSRIT), Bangaluru.
2Dr. Sumana M, Associate Professor, Department of Information Science and Engineering, M S Ramaiah Institute of Technology (MSRIT), Bangaluru.
Manuscript received on April 05, 2020. | Revised Manuscript received on April 19, 2020. | Manuscript published on May 30, 2020. | PP: 271-274 | Volume-9 Issue-1, May 2020. | Retrieval Number: A1388059120/2020©BEIESP | DOI: 10.35940/ijrte.A1388.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Cardiac Arrhythmia is a state within the heart that is caused due to irregular waveforms generated from sinoatrial node. Around 17.3 million people die due o cardiac arrhythmia as indicated by World Health Organization (WHO), the kind of disruptions that is caused by sinoatrial is easily captured in Electrocardiography (ECG) readings; it records in all the disruptions and makes a record in form of images, waveforms, numerical data and categorical data. The noisy data’s collected during a patient examination is recorded in form of a special character to prompt the missing data. With different set of distinct patients having different classes of arrhythmia the ECG easily records in all the arrhythmia class as Y dependent variable’s that is used to pass the collected data from the ECG to the proposed system in the research study, which give’s in an architectural model for detecting arrhythmia with considering a combination of Machine Learning Techniques. Random Forest is mainly used in for feature extraction for the dataset that is trained and tested followed by passing the updated dataset to a combination of different Machine Learning Techniques in order to provide accurate training and testing accuracy results from the dataset received. The use of the proposed model is in hospitals that have huge amount of dataset, with recursive training and testing of the model with the right Machine Learning Algorithm for huge amount of dataset it yields results fast in a short span of time, that can help save several life forms in a very short period of time.
Keywords: Arrhythmia, Prediction, ECG, ML Classifiers, Accuracy.
Scope of the Article: Machine Learning