PREDICTING MYOCARDIAL INFARCTION COMPLICATIONS AND OUTCOMES WITH DEEP LEARNING

Year 2022, Volume: 23 Issue: 2, 184 - 194, 28.06.2022

İsmail Burak Yavru , Sevcan Yılmaz Gündüz

https://doi.org/10.18038/estubtda.1056821

Abstract

Early diagnosis of cardiovascular diseases, which have high mortality rates all over the world, can save many lives. Various clinical findings and past histories of patients play an important role in diagnosing these diseases. These days, the prediction of cardiovascular diseases has gained great importance in the medical field. Pathological studies are prone to misinterpretation because too many findings are studied. For this reason, many automatic models that work with machine learning methods on patients' findings have been proposed. In this study, a model that predicts twelve myocardial infarction complications based on clinical findings is proposed. The proposed model is a deep learning model with three hidden layers with dropouts and a skip connection. A binary accuracy metric is used for measuring the performance of the proposed method. Rectified Linear Unit is set to the hidden layers and sigmoid function to the output layer as an activation function. Experiments were performed on a real dataset with 1700 patient records and carried out on two main scenarios; training on original data and training on augmented data with 100 epochs. As a result of the experiments, a total accuracy rate of 92% was achieved which is the best accuracy rate that has been proposed on this dataset.

Keywords

Deep Learning, Myocardial Infarction, Data Augmentation, Artificial Intelligence, Prediction

PREDICTING MYOCARDIAL INFARCTION COMPLICATIONS AND OUTCOMES WITH DEEP LEARNING

Abstract

Early diagnosis of cardiovascular diseases, which have high mortality rates all over the world, can save many lives. Various clinical findings and past histories of patients play an important role in diagnosing these diseases. These days, the prediction of cardiovascular diseases has gained great importance in the medical field. Pathological studies are prone to misinterpretation because too many findings are studied. For this reason, many automatic models that work with machine learning methods on patients' findings have been proposed. In this study, a model that predicts twelve myocardial infarction complications based on clinical findings is proposed. The proposed model is a deep learning model with three hidden layers with dropouts and a skip connection. A binary accuracy metric is used for measuring the performance of the proposed method. Rectified Linear Unit is set to the hidden layers and sigmoid function to the output layer as an activation function. Experiments were performed on a real dataset with 1700 patient records and carried out on two main scenarios; training on original data and training on augmented data with 100 epochs. As a result of the experiments, a total accuracy rate of 92% was achieved which is the best accuracy rate that has been proposed on this dataset.

Keywords

Deep Learning,, Myocardial Infarction, Data Augmentation, Artificial Intelligence,, Prediction

References

• [1] Timmis A, Townsend N, Gale CP, Torbica A, Lettino M, Petersen SE, Mossialos EA, Maggioni AP, Kazakiewicz D, May HT, et al. European Society of Cardiology: cardiovascular disease statistics 2019. European heart journal, 2020, 41.1: 12-85.
• [2] White HD, Chew DP. Acute myocardial infarction. The Lancet, 2008, 372.9638: 570-584.
• [3] Bassand JP, Hamm CW, Ardissino D, Boersma E, Budaj A, Fernández-Avilés F, Fox KAA, Hasdai D, Ohman RM, Wallentin L, Wijns W, et al. Guidelines for the diagnosis and treatment of non-ST-segment elevation acute coronary syndromes: The Task Force for the Diagnosis and Treatment of Non-ST-Segment Elevation Acute Coronary Syndromes of the European Society of Cardiology. European heart journal, 2007, 28.13: 1598-1660.
• [4] Anderson JL, Adams CD, Antman EM, Bridges CR, Califf RM, Casey DE, Chavey WE, Fesmire FM, Hochman JS, Levin TN, et al. ACC/AHA 2007 guidelines for the management of patients with unstable angina/non–ST-elevation myocardial infarction, Journal of the American College of Cardiology, 2007, 50.7: e1-e157.
• [5] Fox KAA, Steg FG, Eagle KA, Goodman SG, Anderson FA, Granger CB, Flather MD, Budaj A, Quill A, Gore JM. Decline in rates of death and heart failure in acute coronary syndromes, 1999-2006. Jama, 2007, 297.17: 1892-1900.
• [6] Furman MI, Dauerman HL, Goldberg RJ, Yarzbeski J, Lessard D, & Gore JM. Twenty-two year (1975 to 1997) trends in the incidence, in-hospital and long-term case fatality rates from initial Q-wave and non-Q-wave myocardial infarction: a multi-hospital, community-wide perspective. Journal of the American College of Cardiology, 2001, 37.6: 1571-1580..
• [7] Mandelzweig L, Battler A, Boyko V, Bueno H, Danchin N, Filippatos G, Gitt A, Hasdai D, Hasin Y, Marrugat J, et al. The second Euro Heart Survey on acute coronary syndromes: characteristics, treatment, and outcome of patients with ACS in Europe and the Mediterranean Basin in 2004. European heart journal, 2006, 27.19: 2285-2293.
• [8] Liew R, Sulfi S, Ranjadayalan K, Cooper J, Timmis AD. Declining case fatality rates for acute myocardial infarction in South Asian and white patients in the past 15 years. Heart, 2006, 92.8: 1030-1034.
• [9] Jaffe AS, Babuin L, Apple, FS. Biomarkers in acute cardiac disease: the present and the future. Journal of the American college of cardiology, 2006, 48.1: 1-11.
• [10] Antman EM, Cohen M, Bernink PJ, McCabe CH, Horacek T, Papuchis G, Mautner B, Corbalan R, Radley D, Braunwald E. The TIMI risk score for unstable angina/non–ST elevation MI: a method for prognostication and therapeutic decision making. Jama, 2000, 284.7: 835-842.
• [11] Granger CB, Goldberg RJ, Dabbous O, Pieper KS, Eagle KA, Cannon CP, Werf F, Avezum A, Goodman SG, Flather MD, et al. Predictors of hospital mortality in the global registry of acute coronary events. Archives of internal medicine, 2003, 163.19: 2345-2353.
• [12] Huang Y, Wu Z, Wang L, Tan T. Feature coding in image classification: A comprehensive study. IEEE transactions on pattern analysis and machine intelligence, 2013, 36.3: 493-506.
• [13] Schmidhuber J. Deep learning in neural networks: An overview. Neural networks, 2015, 61: 85-117.
• [14] LeCun Y, Bengio Y, Hinton G. Deep learning. nature, 2015, 521.7553: 436-444.
• [15] Min S, Lee B, Yoon S. Deep learning in bioinformatics. Briefings in bioinformatics, 2017, 18.5: 851-869.
• [16] Angermueller C, Pärnamaa T, Parts L, Stegl O. Deep learning for computational biology. Molecular systems biology, 2016, 12.7: 878.
• [17] Ching T, Himmelstein DS, Beaulieu-Jones BK, Kalinin AA, Do BT, Way GP, Ferrero E, Agapow PM, Zietz M, Hoffman MM, et al. Opportunities and obstacles for deep learning in biology and medicine. Journal of The Royal Society Interface, 2018, 15.141: 20170387.
• [18] Swathy M, Saruladha KA. comparative study of classification and prediction of Cardio-Vascular Diseases (CVD) using Machine Learning and Deep Learning techniques. ICT Express, 2021.
• [19] Mienye ID, Sun Y, Wang Z. Improved sparse autoencoder based artificial neural network approach for prediction of heart disease. Informatics in Medicine Unlocked, 2020, 18: 100307.
• [20] Dutta A, Batabyal T, Basu M, Acton ST. An efficient convolutional neural network for coronary heart disease prediction. Expert Systems with Applications, 2020, 159: 113408.
• [21] Golovenkin SE. Myocardial infarction complications Database. University of Leicester, 2020.
• [22] Dorrer MG, Golovenkin SE, Nikulina SY, Orlova YV, Pelipeckaya EY, Vereshchagina TD. Selection of neural network architecture and data augmentation procedures for predicting the course of cardiovascular diseases. In: Journal of Physics: Conference Series. IOP Publishing, 2021. p. 032037.
• [23] Yasue H, Omote S, Takizawa A, Nagao M, Miwa K, Tanaka S. Exertional angina pectoris caused by coronary arterial spasm: effects of various drugs. The American journal of cardiology, 1979, 43.3: 647-652.
• [24] Golovenkin SE, Dorrer MG, Nikulina SY, Orlova YV, Pelipeckaya EY. Evaluation of the effectiveness of using artificial intelligence to predict the response of the human body to cardiovascular diseases. The American journal of cardiology, Journal of Physics: Conference Series, 2020, 1679: 042017