Abstract
Cardiovascular disease (CVD) causes unaffordable social and health costs that tend to increase as the European population ages. In this context, clinical guidelines recommend the use of risk scores to predict the risk of a cardiovascular disease event. Some useful tools have been developed to predict the risk of occurrence of a cardiovascular disease event (e.g. hospitalization or death). However, these tools present some drawbacks. These problems are addressed through two methodologies: (i) combination of risk assessment tools: fusion of naïve Bayes classifiers complemented with a genetic optimization algorithm and (ii) personalization of risk assessment: subtractive clustering applied to a reduced-dimensional space to create groups of patients. Validation was performed based on two ACS-NSTEMI patient data sets. This work improved the performance in relation to current risk assessment tools, achieving maximum values of sensitivity, specificity, and geometric mean of, respectively, 79.8, 83.8, and 80.9 %. Additionally, it assured clinical interpretability, ability to incorporate of new risk factors, higher capability to deal with missing risk factors and avoiding the selection of a standard CVD risk assessment tool to be applied in the clinical practice.
Similar content being viewed by others
References
Alpert J et al (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. J Am College Cardiol 36:959–969
Antman E et al (2000) The TIMI risk score for unstable Angina/non-St elevation MI—a method for prognostication and therapeutic decision making. JAMA 284:835–842
Ayers S et al (2007) Cambridge handbook of psychology, health and medicine. Cambridge University Press, Cambridge. ISBN: 978-0521605106
Bauer E et al (1998) An empirical comparison of voting classification algorithms: bagging, boosting and variants. Mach Learn 36:1–38
Bertrand M et al (2002) Management of acute coronary syndromes in patients presenting without persistent ST-segment elevation. Eur Heart J 23:1809–1840
Boersma E et al (2002) Predictors of outcome in patients with acute coronary syndromes without persistent ST-segment elevation: results from an international trial of 9461 patients. Circulation 101:2557–2657
Bueno H et al (2012) Use of risk scores in acute coronary syndromes. Eur Heart J 98:162–168
CEC/EU (2005) Confronting demographic change: a new solidarity between the generations—Green paper. Commission of the European Communities. http://eur-lex.europa.eu/LexUriServ. Accessed in December 2012
Conroy R et al (2003) Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. Eur Heart J 24:987–1003
Cordella L et al (1999) Reliability parameters to improve combination strategies in multi-expert systems. Pattern Anal Appl 2:205–214
D’Agostino R et al (2008) General cardiovascular risk profile for use in primary care: the Framingham Heart Study. Circulation 117:743–757
EHN (2009) Healthy hearts for all—annual report 2009. European Heart Network. http://www.ehnheart.org/publications/annual-reports.html. Accessed in December 2012
Eiben A et al (2003) Introduction to evolutionary computing. Springer, Berlin. ISBN: 978-3540401841
Friedman N et al (1997) Bayesian network classifiers. Mach Learn 29(131–16):3
Gonçalves P et al (2005) TIMI, PURSUIT and GRACE risk scores: sustained prognostic value and interaction with revascularization in NSTE-ACS. Eur Heart J 26:865–872
Graham I et al (2007) Guidelines on preventing cardiovascular disease in clinical practice: executive summary. Eur Heart J 28:2375–2414
Hammouda K (2000) A comparative study of data clustering techniques. SYDE 625: tools of intelligent systems design. Course Project, University of Waterloo
Han J (2011) Data mining: concepts and techniques, 3rd edn. Morgan Kaufmann. ISBN: 978-0123814791
He H et al (2009) Learning from imbalanced datasets. IEEE Trans Knowl Data Eng 21:1263–1284
Heckerman D, Geiger D, Chickering D (1995) Learning Bayesian networks: the combination of knowledge and statistical data. Mach Learn 20:197–243
Kirkwood B (2002) Medical statistics, 2nd edn. Blackwell Science. ISBN: 978-0-86542-871-2
Lee D et al (2007) Nonlinear dimensionality reduction. Springer, Berlin. ISBN: 978-0387393506
Maaten L et al (2009) Dimensionality reduction: a comparative review. TiCC TR 2009–005, Tilburg University
Nandi R et al (2006) Classification of breast masses in mammograms using genetic programming and feature selection. Med Biol Eng Comput 44:683–694
Reiter H, Maglaveras N (2009) Heartcycle: compliance and effectiveness in HF and CAD closed-loop management. In: Proceedings of the 32nd IEEE EMBC conference, IEEE Press, pp 299–302
Ricotta J et al (2008) Cardiovascular disease management: the need for better diagnostics. Med Biol Eng Comput 46:1059–1068
Samsa G et al (2005) Combining information from multiple data sources to create multivariable risk models: illustration and preliminary assessment of a new method. J Biomed Biotechnol 2:113–123
Siontis G et al (2012) Comparisons of established risk prediction models for cardiovascular disease: systematic review. BMJ 344:e3318
Steyerberg W (2009) Clinical prediction models—a practical approach to development. Validation and updating. Statistics for biology and health. Springer, Berlin. ISBN: 978-0-387-77243-1
Supervised Kotsiantis S, Learning Machine (2007) A review of classification techniques. Informatica 31(249–26):8
Tang E et al (2007) Global Registry of Acute Coronary Events (GRACE) hospital discharge risk scores accurately predicts long term mortality post-acute coronary syndrome. Am Heart J 153:30–35
Tsymbal A et al (2003) Ensemble feature selection with the simple Bayesian classification. Inf Fusion 4:87–100
Twardy C (2005) Knowledge engineering cardiovascular Bayesian networks from the literature. Technical Report 2005/170, Monash University
Webb G et al (2005) Not so naïve Bayes: aggregating one-dependence estimators. Mach Learn 58:5–24
WHO (2009) Cardiovascular diseases (CVDs). World Health Organization, fact sheet n° 317. http://www.who.int/mediacentre/factsheets/fs317. Accessed November 2012)
WHO (2011) BMI classification. World Health Organization. http://apps.who.int/bmi/. Accessed on May 2011
Yan A et al (2007) Risk scores for risk stratification in acute coronary syndromes: useful but simpler is not necessarily better. Eur Heart J 28:1072–1078
Yang Y, Webb G (2002) A comparative study of discretization methods for naïve Bayes classifiers. In: Proceedings of the Pacific Rim knowledge acquisition workshop (PKAW), pp 159–173
Yuan Y (2005) Multiple imputation for missing data: concepts and new development. SAS Institute Inc, Cary
Zheng F et al (2005) A comparative study of semi-naïve Bayes methods in classification learning. In: Proceedings of the 4th Australasian data mining conference, pp 141–156
Zheng W et al (2011) Association between body-mass index and risk of death in more than 1 million Asians. N Engl J Med 364:8
Acknowledgments
This work was supported by HeartCycle EU project (FP7-216695).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Paredes, S., Rocha, T., de Carvalho, P. et al. Integration of Different Risk Assessment Tools to Improve Stratification of Patients with Coronary Artery Disease. Med Biol Eng Comput 53, 1069–1083 (2015). https://doi.org/10.1007/s11517-015-1342-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-015-1342-3