Diagnosis of Acute Myocardial Infarction using Random Forest Classifier Through SPECT
Dhilsath Fathima M1, Hariharan R2, Leena Christy M3, S. EbenazerRoselin4
1Dhilsath Fathima. M, Assistant Professor, in Vel Tech Rangarajan.
2R. Hariharan, Assistant Professor, in Veltech Deemed to Be university
3Leena Christy M, Assistant Professor, at Aalimmuhammedsalegh College of Engineering.
4Mrs.S. Ebenazer Roselin, Assistant Professor, in Prince Dr K Vasudevan College of Engineering and Technology.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 1678-1682 | Volume-8 Issue-7, May 2019 | Retrieval Number: F4057048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Acute Myocardial Infarction (MI) is a severe heart disease which is caused by abruptly reduced blood supply in coronary arteries due to prolonged ischemia condition. It is a type of irreversible necrosis of cardiac muscles, so need to predict this Acute MI in early stages of cardiac ischemia. This paper presents a new computer- aided diagnosis system (CAD) for the early prediction of Acute Myocardial infarction(MI) based on the machine learning algorithms using Myocardial perfusion single photon emission computed tomography(SPECT) images. Myocardial perfusion SPECT image database containing processed SPECT images collected from the 267 patients at cardiac rest study and cardiac stress study to examine the heart blood supply. This processed data are trained using random forest learning algorithm and a result of this proposed model is compared with other six machine learning algorithms. Eight Performance metrics of machine learning are used to evaluate the output of this proposed model. This CAD system helps to evaluate the presence of MI in the cardiac SPECT images, reduce the diagnosis cost due to automation learning and save the life of the cardiac patients
Keyword: Acute Myocardial Infarction, Myocardial Perfusion SPECT, Machine Learning, Medical Image Analysis, Random Forest Algorithm
Scope of the Article: Design and Diagnosis.