Enhancing Coronary Artery Diseases Screening: A Comprehensive Assessment of Machine Learning Approaches Using Routine Clinical and Laboratory Data.

Shahryar Naji, Zahra Niazkhani, Kamal Khadem vatan, Habibollah Pirnejad
67

Views


Abstract

Introduction: Coronary artery disease (CAD) stands among the leading global causes of mortality, underscoring the critical necessity for early detection to facilitate effective treatment. Although Coronary Angiography (CA) serves as the gold standard for diagnosis, its limitations for screening, including side effects and cost, necessitate alternative approaches. This study focuses on the development and comparison of machine learning techniques as substitutes for CA in CAD screening, leveraging routine clinical and laboratory data.

Material and Methods: Various machine learning classification algorithms—decision tree, k-nearest neighbor, artificial neural network, support vector machine, logistic regression, and stacked ensemble learning—were employed to differentiate CAD and healthy subjects. Feature selection algorithms, namely LASSO and ReliefF, were utilized to prioritize relevant features. A range of evaluation metrics, including accuracy, precision, sensitivity, specificity, AUC, F1 score, ROC curve, and NPV, were applied. The SHAP technique was employed to elucidate and interpret the artificial neural network model.

Results: The artificial neural network, support vector machine, and stacked ensemble learning models demonstrated excellent results in a 10-fold cross-validation evaluation using features selected by LASSO and ReliefF. With the LASSO feature selection algorithm, these models achieved accuracies of 90.38%, 90.07%, and 90.39%, sensitivities of 94.43%, 93.03%, and 93.96%, and specificities of 80.27%, 82.77%, and 81.52%, respectively. Using ReliefF, the accuracies were 88.79%, 88.77%, and 90.06%, sensitivities were 92.12%, 91.66%, and 93.98%, and specificities were 80.13%, 81.38%, and 80.13%, respectively. The SHAP technique revealed that typical and atypical chest pain, hypertension, diabetes mellitus, T inversion, and age were the most influential features in the neural network model.

Conclusion: The machine learning models developed in this study exhibit high potential for non-invasive screening and diagnosis of CAD in the Z-Alizadeh Sani dataset. However, further studies are essential to validate and apply these models in real-world and clinical settings.

Keywords

Coronary Artery Disease; Coronary Angiography; Machine Learning; Artificial Intelligence;

References

Marateb HR, Goudarzi S. A noninvasive method for coronary artery diseases diagnosis using a clinically-interpretable fuzzy rule-based system. J Res Med Sci. 2015; 20(3): 214-23. PMID: 26109965

Gopalan C, Kirk E. Coronary artery disease. In: Gopalan C, Kirk E. Biology of cardiovascular and metabolic diseases. Academic Press; 2022.

Ghadiri Hedeshi N, Saniee Abadeh M. Coronary artery disease detection using a fuzzy-boosting PSO approach. Comput Intell Neurosci. 2014; 2014: 783734. PMID: 24817883 DOI: 10.1155/2014/783734

Zeitouni M, Clare RM, Chiswell K, Abdulrahim J, Shah N, Pagidipati NP, et al. Risk factor burden and long-term prognosis of patients with premature coronary artery disease. J Am Heart Assoc. 2020; 9(24): e017712. PMID: 33287625 DOI: 10.1161/JAHA.120.017712

Kim JK, Kang S. Neural network-based coronary heart disease risk prediction using feature correlation analysis. J Healthc Eng. 2017; 2017: 2780501. PMID: 29076332 DOI: 10.1155/2017/2780501

Ali L, Rahman A, Khan A, Zhou M, Javeed A, Khan JA. An automated diagnostic system for heart disease prediction based on chi-squared statistical model and optimally configured deep neural network. IEEE Access. 2019; 7: 34938-45.

Zhenya Q, Zhang Z. A hybrid cost-sensitive ensemble for heart disease prediction. BMC Med Inform Decis Mak. 2021; 21(1): 73. PMID: 33632225 DOI: 10.1186/s12911-021-01436-7

Sarrafzadegan N, Mohammmadifard N. Cardiovascular disease in Iran in the last 40 years: Prevalence, mortality, morbidity, challenges and strategies for cardiovascular prevention. Arch Iran Med. 2019; 22(4): 204-10. PMID: 31126179

Fox KAA, Metra M, Morais J, Atar D. The myth of 'stable' coronary artery disease. Nat Rev Cardiol. 2020; 17(1): 9-21. PMID: 31358978 DOI: 10.1038/s41569-019-0233-y

Lahsasna A, Ainon RN, Zainuddin R, Bulgiba A. Design of a fuzzy-based decision support system for coronary heart disease diagnosis. J Med Syst. 2012; 36(5): 3293-306. PMID: 22252606 DOI: 10.1007/s10916-012-9821-7

Corrado D, Thiene G, Pennelli N. Sudden death as the first manifestation of coronary artery disease in young people (less than or equal to 35 years). Eur Heart J. 1988; 9(Suppl N): 139-44. PMID: 3246245 DOI: 10.1093/eurheartj/9.suppl_n.139

Mehta D, Curwin J, Gomes JA, Fuster V. Sudden death in coronary artery disease: Acute ischemia versus myocardial substrate. Circulation. 1997; 96(9): 3215-23. PMID: 9386195 DOI: 10.1161/01.cir.96.9.3215

Huang X, Rosenthal MB. Overuse of cardiovascular services: Evidence, causes, and opportunities for reform. Circulation. 2015; 132(3): 205-14. PMID: 26195488 DOI: 10.1161/CIRCULATIONAHA.114.012668

Bradley SM, Maddox TM, Stanislawski MA, O'Donnell CI, Grunwald GK, Tsai TT, et al. Normal coronary rates for elective angiography in the veterans affairs healthcare system: Insights from the VA CART program (veterans affairs clinical assessment reporting and tracking). J Am Coll Cardiol. 2014; 63(5): 417-26. PMID: 24184244 DOI: 10.1016/j.jacc.2013.09.055

Thomas MP, Gurm HS, Nallamothu BK. When is it right to be wrong? J Am Coll Cardiol. 2014; 63(5): 427-9. PMID: 24184239 DOI: 10.1016/j.jacc.2013.10.010

Joshi H, Shah R, Prajapati J, Bhangdiya V, Shah J, Kandre Y, et al. Diagnostic accuracy of computed tomography angiography as compared to conventional angiography in patients undergoing noncoronary cardiac surgery. Heart Views. 2016; 17(3): 88-91. PMID: 27867455 DOI: 10.4103/1995-705X.192555

Montalescot G, Sechtem U, Achenbach S, Andreotti F, Arden C, Budaj A, et al. 2013 ESC guidelines on the management of stable coronary artery disease: The task force on the management of stable coronary artery disease of the European society of cardiology. Eur Heart J. 2013; 34(38): 2949-3003. PMID: 23996286 DOI: 10.1093/eurheartj/eht296

Abbara S, Arbab-Zadeh A, Callister TQ, Desai MY, Mamuya W, Thomson L, et al. SCCT guidelines for performance of coronary computed tomographic angiography: A report of the Society of cardiovascular computed tomography guidelines committee. J Cardiovasc Comput Tomogr. 2009; 3(3): 190-204. PMID: 19409872 DOI: 10.1016/j.jcct.2009.03.004

Chan PS, Patel MR, Klein LW, Krone RJ, Dehmer GJ, Kennedy K, et al. Appropriateness of percutaneous coronary intervention. JAMA. 2011; 306(1): 53-61. PMID: 21730241 DOI: 10.1001/jama.2011.916

Ko DT, Guo H, Wijeysundera HC, Natarajan MK, Nagpal AD, Feindel CM, et al. Assessing the association of appropriateness of coronary revascularization and clinical outcomes for patients with stable coronary artery disease. J Am Coll Cardiol. 2012; 60(19): 1876-84. PMID: 23062534 DOI: 10.1016/j.jacc.2012.06.056

Korenstein D, Falk R, Howell EA, Bishop T, Keyhani S. Overuse of health care services in the United States: an understudied problem. Arch Intern Med. 2012; 172(2): 171-8. PMID: 22271125 DOI: 10.1001/archinternmed.2011.772

Lipitz-Snyderman A, Bach PB. Overuse of health care services: When less is more ... more or less. JAMA Intern Med. 2013; 173(14): 1277-8. PMID: 23712254 DOI: 10.1001/jamainternmed.2013.6181

Joynt KE. Rightsizing invasive cardiac services in the United States. Circulation. 2013; 128(8): 780-2. PMID: 23877257 DOI: 10.1161/CIRCULATIONAHA.113.004718

Carr JJ, Hendel RC, White RD, Patel MR, Wolk MJ, Bettmann MA, et al. 2013 appropriate utilization of cardiovascular imaging: A methodology for the development of joint criteria for the appropriate utilization of cardiovascular imaging by the American college of cardiology foundation and American college of radiology. J Am Coll Cardiol. 2013; 61(21): 2199-206. PMID: 23500292 DOI: 10.1016/j.jacc.2013.02.010

Gokulnath C, Shantharajah SP. An optimized feature selection based on genetic approach and support vector machine for heart disease. Cluster Computing. 2019; 22: 14777-87.

Das R, Turkoglu I, Sengur A. Effective diagnosis of heart disease through neural networks ensembles. Expert Systems with Applications. 2009; 36(4): 7675-80.

Mohan S, Thirumalai C, Srivastava G. Effective heart disease prediction using hybrid machine learning techniques. IEEE Access. 2019; 7: 81542-54.

Forrest I, Petrazzini B, Duffy Á, Park J, Marquez-Luna C, Jordan D, et al. Machine learning-based marker for coronary artery disease: Derivation and validation in two longitudinal cohorts. The Lancet. 2022; 401(10372): 215-25.

Alizadehsani R, Habibi J, Hosseini MJ, Mashayekhi H, Boghrati R, Ghandeharioun A, et al. A data mining approach for diagnosis of coronary artery disease. Comput Methods Programs Biomed. 2013; 111(1): 52-61. PMID: 23537611 DOI: 10.1016/j.cmpb.2013.03.004

Norgeot B, Quer G, Beaulieu-Jones BK, Torkamani A, Dias R, Gianfrancesco M, et al. Minimum information about clinical artificial intelligence modeling: The MI-CLAIM checklist. Nat Med. 2020; 26(9): 1320-4. PMID: 32908275 DOI: 10.1038/s41591-020-1041-y

Alizadehsani R, Habibi J, Hosseini MJ, Boghrati R, Ghandeharioun A, Bahadorian B, et al. Diagnosis of coronary artery disease using data mining techniques based on symptoms and ECG features. European Journal of Scientific Research. 2012; 82(4): 542-53.

Braunwald E, Bonow RO. Braunwald's heart disease: A textbook of cardiovascular medicine. 9th ed. Saunders; 2012.

Lustgarten JL, Gopalakrishnan V, Grover H, Visweswaran S. Improving classification performance with discretization on biomedical datasets. AMIA Annu Symp Proc. 2008; 2008: 445-9. PMID: 18999186

Tibshirani R. Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society Series B. 1996; 58(1): 267-88.

Urbanowicz RJ, Olson RS, Schmitt P, Meeker M, Moore JH. Benchmarking relief-based feature selection methods for bioinformatics data mining. J Biomed Inform. 2018; 85: 168-88. PMID: 30030120 DOI: 10.1016/j.jbi.2018.07.015

Alizadehsani R, Abdar M, Roshanzamir M, Khosravi A, Kebria PM, Khozeimeh F, et al. Machine learning-based coronary artery disease diagnosis: A comprehensive review. Comput Biol Med. 2019; 111: 103346. PMID: 31288140 DOI: 10.1016/j.compbiomed.2019.103346

Geron A. Hands-on machine learning with scikit-learn, keras, and tensorFlow: Concepts, tools, and techniques to build intelligent systems. O'Reilly Media, Inc.; 2019.

Cortes C, Vapnik V. Support-vector networks. Machine Learning. 1995; 20(3): 273-97.

Larsen K, Petersen J, Budtz-Jørgensen E, Endahl L. Interpreting parameters in the logistic regression model with random effects. Biometrics. 2000; 56(3): 909-14. PMID: 10985236 DOI: 10.1111/j.0006-341x.2000.00909.x

Uguroglu S, Carbonell J, Doyle M, Biederman R. Cost-sensitive risk stratification in the diagnosis of heart disease. Innovative Appications of Artificial Intelligence Conference. Association for the Advancement of Artificial Intelligence; 2012.

Wolpert DH. Stacked generalization. Neural Networks. 1992; 5(2): 241-59.

Witten IH, Frank E, Hall MA. Data mining: Practical machine learning tools and techniques. Morgan Kaufmann Publishers Inc.; 2011.

Lundberg SM, Nair B, Vavilala MS, Horibe M, Eisses MJ, Adams T, et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat Biomed Eng. 2018; 2(10): 749-60. PMID: 31001455 DOI: 10.1038/s41551-018-0304-0

Arabasadi Z, Alizadehsani R, Roshanzamir M, Moosaei H, Yarifard AA. Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm. Comput Methods Programs Biomed. 2017; 141: 19-26. PMID: 28241964 DOI: 10.1016/j.cmpb.2017.01.004

Hassannataj Joloudari J, Azizi F, Nematollahi MA, Alizadehsani R, Hassannatajjeloudari E, Nodehi I, et al. GSVMA: A genetic support vector machine ANOVA method for CAD diagnosis. Front Cardiovasc Med. 2022; 8: 760178. PMID: 35187099 DOI: 10.3389/fcvm.2021.760178

Velusamy D, Ramasamy K. Ensemble of heterogeneous classifiers for diagnosis and prediction of coronary artery disease with reduced feature subset. Comput Methods Programs Biomed. 2021; 198: 105770. PMID: 33027698 DOI: 10.1016/j.cmpb.2020.105770

Joloudari JH, Joloudari EH, Saadatfar H, GhasemiGol M, Razavi SM, Mosavi A, et al. Coronary artery disease diagnosis: Ranking the significant features using a random trees model. Int J Environ Res Public Health. 2020; 17(3): 731. PMID: 31979257 DOI: 10.3390/ijerph17030731

Ghiasi MM, Zendehboudi S, Mohsenipour AA. Decision tree-based diagnosis of coronary artery disease: CART model. Comput Methods Programs Biomed. 2020; 192: 105400. PMID: 32179311 DOI: 10.1016/j.cmpb.2020.105400

Dahal K, Gautam Y. Argumentative comparative analysis of machine learning on coronary artery disease. Open Journal of Statistics. 2020; 10: 694-705.

Cüvitoğlu A, Işik Z. Classification of CAD dataset by using principal component analysis and machine learning approaches. International Conference on Electrical and Electronic Engineering. IEEE; 2018.

The Lancet Respiratory Medicine. Opening the black box of machine learning. Lancet Respir Med. 2018; 6(11): 801. PMID: 30343029 DOI: 10.1016/S2213-2600(18)30425-9

Davies SW. Clinical presentation and diagnosis of coronary artery disease: Stable angina. Br Med Bull. 2001; 59: 17-27. PMID: 11756201 DOI: 10.1093/bmb/59.1.17

Hickam DH. Chest pain or discomfort. In: Walker HK, Hall WD, Hurst JW (eds). Clinical methods: The history, physical, and laboratory examinations. Butterworth Publishers; 1990.

Park HW, Kang MG, Kim K, Koh JS, Park JR, Jeong YH, et al. Long-term prognosis and clinical characteristics of patients with newly diagnosed diabetes mellitus detected after first acute myocardial infarction: From KAMIR-NIH registry. Korean Circ J. 2018; 48(2): 134-47. PMID: 29441746 DOI: 10.4070/kcj.2017.0174

Weber T, Lang I, Zweiker R, Horn S, Wenzel RR, Watschinger B, et al. Hypertension and coronary artery disease; epidemiology, physiology, effects of treatment, and recommendations : A joint scientific statement from the Austrian society of cardiology and the Austrian society of hypertension. Wien Klin Wochenschr. 2016; 128(13-14): 467-79. PMID: 27278135 DOI: 10.1007/s00508-016-0998-5

Slack D, Hilgard S, Jia E, Singh S, Lakkaraju H. Fooling lime and SHAP: Adversarial attacks on post hoc explanation methods. Conference on AI, Ethics, and Society. ACM; 2020.

Molnar C. Interpretable machine learning: A guide for making black box models explainable. 2nd ed. 2022.




DOI: https://doi.org/10.30699/fhi.v13i0.555

Refbacks

  • There are currently no refbacks.