Abstract
In the last several decades the development of information-communication technology (ICT) and related fields has assisted medicine in many aspects. This paper tends to contribute to this ongoing trend by testing the accuracy of probabilistic neural network (PNN) trained to determine the results of cardiac stress test used for diagnosis of coronary/ischemic heart disease (CHD). The obtained results show that the network can determine the patients who really need immediate diagnosis treatments in the shortest time with the satisfactory accuracy. Therefore, the proposed simulations can be used for the physicians in the training process and additionally ease the work to cardiologists and improve the treatment of cardiac patients.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Belhachat, F., Izeboudjen, N.: Application of a Probabilistic Neural Network for Classification of Cardiac Arrhytmias. In: 13th International Research/Expert Conference, TMT 2009, Hammamet, Tunisia (2009)
NHS Choices, Coronary Heart Disease, http://www.nhs.uk/conditions/Coronary-heart-disease/Pages/Introduction.aspx
Mahmoudi, I., Askari Moghadam, R., Moazzam, M., Sadeghian, S.: Prediction Model for Coronary Artery Disease Using Neural Networks and Feature Selection Based on Classification and Regression Tree. Shahrekord University of Medical Sciences, 15(5), 47-56 (2013)
Khosravanian, A., Ayat, S.: Designing and Evaluation of a Decision Support System for Prediction of Coronary Artery Disease. Hormozgan Medical Journal, 19(6) (2016)
Ballestas, H. C., et al.: ECG Strip Ease: An Arrhythmia Interpretation Workbook. Lippincott Williams & Wilkins, Philadelphia (2007)
Stein, E.: Rapid Analysis of electrocardiograms: A Self-Study Program. Lippincott Williams & Wilkins, Philadelphia (2000)
Life in the Fast line, http://lifeinthefastlane.com/ecg-library/st-segment/
Chung, S. N.: Textbook of Clinical Electrocardiography for Postgraduates, Resident Doctors and Practicing Physicians. Jaypee Brothers Medical Publishers, New Delhi (2012)
Specht, D. F.: Probabilistic Neural Networks for Classification, Mapping, or Associative Memory. In: IEEE International Conference on Neural Networks, IEEE Press (1988)
Kusy, M., Zajdel, R.: Probabilistic Neural Network Training Procedure Based on Q(o)-learning Algorithm in Medical Data Classification. Appl Intell., 41(3), 837-854 (2014)
Sarma, M., Sarma, K. K.: Phoneme-Based Speech Segmentation Using Hybrid Soft Computing framework. Springer India (2014)
Dubey, V., Richariya, V.: A Neural Network Approach for ECG Classification. International Journal of Emerging Technology and Advanced Engineering, 3(10), 189-196 (2013)
Mohapatra, S.: Classification of Electrocardiogram Waveforms Using PNN. National Institute of Technology Rourkela, (2010)
Bulusu, S.C., et al.: Transient ST-Segment Episode Detection for ECG Beat Classification. In: IEEE/NIH Life Science Systems and Applications Workshop (LiSSA), (2011)
Banupriya, C.V., Karpagavalli, S.: Electrocardiogram Beat Classification Using Probabilistic Neural Network. International Journal of Computer Applications Proceedings on Machine Learning: Challenges and Opportunities Ahead, (2014)
Lin, C., Chen, P., Chen, T.: Cardiac Arrhythmia Recognition Using Wavelet-probabilistic Network. In: Proceedings of the Automatic Control Conference (CACS 2005). Tainan, Taiwn, (2005)
Jeong, G.Y., Yu, K.H.: Design of Ambulatory ECG Monitoring System to Detect ST Pattern Change. In: SICE-ICASE International Joint Conference, (2006)
Borovinskiy, V., Potočnik, P.: Classification of Iris Data Set. University of Ljubljana, (2009).
Baraković, S., Banjanović-Mehmedović, L.: Probabilističke neuronske mreže. University of Tuzla, (2009).
Zheng, C.Y., For K-fold Cross Validation, What K Should Be Selected?, https://www.quora.com/For-K-fold-cross-validation-what-k-should-be-selected
Choice of K in K-fold Cross Validation, http://stats.stackexchange.com/questions/27730/choice-of-k-in-k-fold-cross-validation
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Baraković, S., Husić, J.B., Baraković, F. (2017). Determination of Probabilistic Neural Network’s Accuracy in Context of Cardiac Stress Test. In: Badnjevic, A. (eds) CMBEBIH 2017. IFMBE Proceedings, vol 62. Springer, Singapore. https://doi.org/10.1007/978-981-10-4166-2_37
Download citation
DOI: https://doi.org/10.1007/978-981-10-4166-2_37
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-4165-5
Online ISBN: 978-981-10-4166-2
eBook Packages: EngineeringEngineering (R0)