Abstract
In the PREVENIR-5 study, artificial neural networks (NN) were applied to a large sample of patients with recent first acute coronary syndrome (ACS) to identify determinants of persistence of evidence-based cardiovascular medications (EBCM: antithrombotic + beta-blocker + statin + angiotensin converting enzyme inhibitor-ACEI and/or angiotensin-II receptor blocker-ARB). From October 2006 to April 2007, 1,811 general practitioners recruited 4,850 patients with a mean time of ACS occurrence of 24 months. Patient profile for EBCM persistence was determined using automatic rule generation from NN. The prediction accuracy of NN was compared with that of logistic regression (LR) using Area Under Receiver-Operating Characteristics-AUROC. At hospital discharge, EBCM was prescribed to 2,132 patients (44%). EBCM persistence rate, 24 months after ACS, was 86.7%. EBCM persistence profile combined overweight, hypercholesterolemia, no coronary artery bypass grafting and low educational level (Positive Predictive Value = 0.958). AUROC curves showed better predictive accuracy for NN compared to LR models.
Similar content being viewed by others
References
Agatonovic-Kustrin S, Beresford R (2000) Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed Anal 22:717–727
Ali RC, Melloni C, Ou FS, Schmader K, Ohman EM, Roe MT, Peterson ED, Alexander KP (2009) Age and persistent use of cardiovascular medication after acute coronary syndrome: results from medication applied and sustained over time. JAGS 57:1990–1996
Amar J, Ferrières J, Cambou JP, Amelineau E, Danchin N (2008) Persistence of combination of evidence-based medical therapy in patients with acute coronary syndromes. Arch Cardiovasc Dis 101:301–306
Baldassarre D, Grossi E, Buscema M, Intraligi M, Amato M, Tremoli E, Pustina L, Castelnuovo S, Sanvito S, Gerosa L, Sirtori CR (2004) Recognition of patients with cardiovascular disease by artificial neural networks. Ann Med 36:630–640
Bassand JP, Hamm CW, Ardissino D, Boersma E, Budaj A, Fernández-Avilés F, Fox KA, Hasdai D, Ohman EM, Wallentin L, Wijns W (2007) Guidelines for the diagnosis and treatment of non-ST-segment elevation acute coronary syndromes. ESC Guidelines. Eur Heart J 28:1598–1660
Bigi R, Gregori D, Cortigiani L, Desideri A, Chiarotto FA, Toffolo GM (2005) Artificial neural networks and robust Bayesian classifiers for risk stratification following uncomplicated myocardial infarction. Int J Cardiol 101:481–487
Bourdès V, Bonnevay S, Lisboa PJ, Defrance R, Pérol D, Chabaud S, Bachelot T, Gargi T, Négrier S (2010) Comparison of artificial neural network with logistic regression as classification models for variable selection for prediction of breast cancer patient outcomes. Advances in Artificial Neural Systems 2010, Article ID 309841
Carruthers KF, Dabbous OH, Flather MD, Starkey I, Jacob A, Macleod D, Fox KA, GRACE Investigators (2005) Contemporary management of acute coronary syndromes: does the practice match the evidence? The global registry of acute coronary events (GRACE). Heart 91:290–298
Cross SS, Harrison FR, Kennedy RL (1995) Introduction to neural networks. Lancet 346:1075–1079
Danchin N, Cambou JP, Hanania G, Kadri Z, Genès N, Lablanche JM, Blanchard D, Vaur L, Clerson P, Guéret P, USIC 2000 investigators (2005) Impact of combined secondary prevention therapy after myocardial infarction: data from a nationwide French registry. Am Heart J 150:1147–1153
Eagle KA, Kline-Rogers E, Goodman SG, Gurfinkel EP, Avezum A, Flather MD, Granger CB, Erickson S, White K, Steg PG (2004) Adherence to evidence-based therapies after discharge for acute coronary syndromes: an ongoing prospective, observational study. Am J Med 117:73–81
Etchells TA, Harrison MJ (2006) Orthogonal search-based rule extraction for modelling the decision to transfuse. Anaesthesia 61:335–338
Etchells TA, Lisboa PJ (2006) Orthogonal search-based rule extraction (OSRE) for trained neural networks: a practical and efficient approach. IEEE Trans Neural Networks 17:374–384
EUROASPIRE II Study Group (2001) Lifestyle and risk factor management and use of drug therapies in coronary patients from 15 countries; principal results from EUROASPIRE II Euro Heart Survey Programme. Eur Heart J 22:554–572
Feely J, Chan R, McManus J, O’Shea B (1999) The influence of hospital-based prescribers on prescribing in general practice. Pharmacoeconomics 16:175–181
Goldberg DE (1989) Genetic algorithms in search optimization and machine learning. Kluwer Academic Publishers, Boston
Grech ED, Ramsdale DR (2003) Acute coronary syndrome: unstable angina and non-ST segment elevation myocardial infarction. Brit Med J 326:1259–1261
Harder S, Thürmann P, Thierolf C, Klepzig H (1998) Prescription of cardiovascular drugs in outpatient care: a survey of outpatients in a German university hospital. Int J Clin Pharmacol Ther 36:195–201
Hasdai D, Behar S, Wallentin L, Danchin N, Gitt AK, Boersma E, Fioretti PM, Simoons ML, Battler A (2002) A prospective survey of the characteristics, treatments and outcomes of patients with acute coronary syndromes in Europe and the Mediterranean basin; the Euro Heart Survey of Acute Coronary Syndromes (Euro Heart Survey ACS). Eur Heart J 23:1190–1201
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward neural networks are universal approximators. Neural Networks 2:259–366
International Epidemiological Association (IEA). Good Epidemiological Practice (GEP). IEA guidelines for proper conduct in epidemiologic research (2007). http://www.ieaweb.org
Jackevicius CA, Mamdani M, Tu JV (2002) Adherence with statin therapy in elderly patients with and without acute coronary syndromes. JAMA 288:462–467
Joint European Society of Cardiology/American College of Cardiology Committee (2000) Myocardial infarction redefined–a consensus document of The Joint European Society of Cardiology/American College of Cardiology Committee for the redefinition of myocardial infarction. Eur Heart J 21:1502–1513
Jones JK, Gorkin L, Lian JF, Staffa JA, Fletcher AP (1995) Discontinuation of and changes in treatment after start of new courses of antihypertensive drugs: a study of a United Kingdom population. Brit Med J 311:293–295
Krumholz HM, Vaccarino V, Ellerbeck EF, Kiefe C, Hennen J, Kresowik TF, Gold JA, Jencks SF, Radford MJ (1997) Determinants of appropriate use of angiotensin-converting enzyme inhibitors after acute myocardial infarction in persons > or = 65 years of age. Am J Cardiol 79:581–586
Kulkarni SP, Alexander KP, Lytle B, Heiss G, Peterson ED (2006) Long-term adherence with cardiovascular drug regimens. Am Heart J 151:185–191
Lee HY, Cooke CE, Robertson TA (2008) Use of secondary prevention drug therapy in patients with acute coronary syndrome after hospital discharge. J Manag Care Pharm 14:271–280
Philippe F, Cambou JP, Danchin N, Thomas D (2005) Changes in the prescription of cardiovascular prevention drugs in France between 1995 and 2003: factors influencing the gap between evidence base medicine and clinical practice. Ann Cardiol Angeiol 54(Suppl 1):S30–S36
Ramanath VS, Eagle KA (2007) Evidence-based medical therapy of patients with acute coronary syndromes. Am J Cardiovasc Drugs 7:95–116
Roe CM, Motheral BR, Teitelbaum F, Rich MW (2000) Compliance with and dosing of angiotensin-converting-enzyme inhibitors before and after hospitalization. Am J Health Syst Pharm 57:139–145
Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65:386–408
Silber S, Albertsson P, Fernandez-Avilès F, Camici PG, Colombo A, Hamm C, Jørgensen E, Marco J, Nordrehaug JE, Ruzyllo W, Urban P, Stone GW, Wijns W, Task Force for Percutaneous Coronary Interventions of the European Society of Cardiology (2005) Guidelines for percutaneous coronary interventions. ESC Guidelines. Eur Heart J 26:804–807
Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49:1225–1231
Van de Werf F, Ardissino D, Betriu A, Cokkinos DV, Falk E, Fox KA, Julian D, Lengyel M, Neumann FJ, Ruzyllo W, Thygesen C, Underwood SR, Vahanian A, Verheugt FW, Wijns W, Task Force on the Management of Acute Myocardial Infarction of the European Society of Cardiology (2003) Management of acute myocardial infarction in patients presenting with ST-segment elevation. ESC Guidelines. Eur Heart J 24:28–66
Voss R, Cullen P, Schulte H, Assmann G (2002) Prediction of risk of coronary events in middle-aged men in the Prospective Cardiovascular Munster Study (PROCAM) using neural networks. Int J Epidemiol 31:1253–1562
Yan AT, Yan RT, Tan M, Huynh T, Soghrati K, Brunner LJ, DeYoung P, Fitchett DH, Langer A, Goodman SG, Canadian ACS Registries Investigators (2007) Optimal medical therapy at discharge in patients with acute coronary syndromes: temporal changes, characteristics, and 1-year outcome. Am Heart J 154:1108–1115
Acknowledgments
This study was financially supported by Bristol Myers Squibb, France. The authors thank Prof. Paulo Lisboa and his team (Liverpool John Moore University, United Kingdom) for the rule extraction methodology and the data management and statistics department of ICTA-PM (Dijon, France).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bourdès, V., Ferrières, J., Amar, J. et al. Prediction of persistence of combined evidence-based cardiovascular medications in patients with acute coronary syndrome after hospital discharge using neural networks. Med Biol Eng Comput 49, 947–955 (2011). https://doi.org/10.1007/s11517-011-0785-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-011-0785-4