Open Access Open Access  Restricted Access Subscription or Fee Access

Design and Development of Tool to Predict Heart Diseases

Anagha Ramane, M.M Wankhade

Abstract


Sudden Cardiac Arrest is one of the major causes for death. Death is due to loss of functioning of heart. Cardiac arrhythmias and coronary heart diseases are two main reasons leading to cardiac arrest. The diseases which lead to cardiac arrest are Ischemia, Myocardial Infarction, Chamber
enlargement, Sinus node problem. ECG is an important diagnostic tool for assessing heart condition. The cardiac diseases mentioned above affect ECG. Thus, ECG can be used to investigate possible
abnormalities in the heart and prevent death. The paper discusses the tool developed that can be used to diagnose the above diseases from the ECG at early stage to preventive action in time. The tool
developed in the paper, diagnoses a patient, if he is suffering from a heart disease by analyzing the ECG. In developing the tool, initial part done is to digitize the scanned ECG image. For digitizing the
ECG image different morphological operations have being used. At the last the digitized image is being stored in vector form. Then the features of ECG i.e., P, QRS-T waves would be extracted. Thus,
after feature extraction, these features would be used to diagnose the above mentioned abnormalities in heart. The ECG is analyzed, and the changed features of ECG (P-wave, QRS complex and T wave
amplitude and intervals) are extracted, the disease is predicted by the program developed using python language and advise is given to the patient if he should consult to a cardiologist. The tool developed is simple, user friendly and handy.


Full Text:

PDF

References


A. Peterkova, M. Stremy, The raw ECG signal processing and the detection of QRS complex, 2015 IEEE European Modelling Symposium, 2015.

Suma C. Bulusu, Miad Faezipour, Vincent Ng, Mehrdad Nourani, Lakshman S. Tamil, Transient ST-Segment Episode Detection for ECG Beat Classification, NIH Life Science Systems and Applications Workshop(LiSSA),Bethesda,MD, USA;2011 IEEE.21 April.

Hla Myo Tun, Win Khaing Moe, Zaw Min Naing, Analysis on conversion process from paper record ECG to computer based ECG, MOJ App Bio Biomech, September 2017Vol1(2).

Boussaa Mohamed, Atouf Issam, Atibi ,et al; ECG image classification in real time based on the haar-like features and artificial neural networks, The International Conference on Advanced Wireless, Information and Communication Technologies, ScienceDirect, Vol73, 2015.Pp32-39.

Atandra Burman, Jitto Titus, David Gbadebo, ECG Detect: Detecting Ischemia Via Deep Learning, 28‒ September 2020.

International Journal of Radio Frequency Design

Volume 7, Issue 1

© JournalsPub 2021. All Rights Reserved 16

Costas Papaloukas, Dimitrios I. Fotiadis, Aristidis Likas, Lampros K. Michalis, An ischemia detection method based on artificial neural networks, Artificial Intelligence in Medicine 24, Elsevier 2002,Pp 167-178.

Till Braun, Sotirios Spiliopoulous et al., Detection of myocardial Ischemia due to clinically asymptomatic coronary artery stenosis at rest using Supervised Artificial Intelligence-enabled vectorcardiography- A five-fold cross validation of accuracy, Elsevier, Journal of Electrocardiology, 2020;Vol59; Pp100-105.

G. Angelo Virgin, V. Vijaya Bhaskar, Conversion of ECG Graph into Digital Format, International Journal of Pure and Applied Mathematics, January 2018, Vol 118,. 17.

Cong Wang, Xunde Dong, Shanxing Ou, Wei Wang, Junmin Hu, Feifei Yang, A new method for early detection of myocardial ischemia: cardiodynamicsgram (CDG), Science China, Information Sciences, January 2016, Vol 59:1Pp1-11.

Ary L. Goldberger, Zachary D. Goldberger, Alexei Shvilkin, Goldberger’s, Clinical Electrocardiography A Simplified Approach, Elsevier Saunders ,9th Edition,:Elsevier;2017




DOI: https://doi.org/10.37628/jrfd.v7i1.1514

Refbacks

  • There are currently no refbacks.