Skip to main content
PMC home page
Proceedings of the AMIA Symposium logoLink to Proceedings of the AMIA Symposium
. 2000:156–160.

Models to predict cardiovascular risk: comparison of CART, multilayer perceptron and logistic regression.

I Colombet 1, A Ruelland 1, G Chatellier 1, F Gueyffier 1, P Degoulet 1, M C Jaulent 1
PMCID: PMC2244093  PMID: 11079864

Abstract

The estimate of a multivariate risk is now required in guidelines for cardiovascular prevention. Limitations of existing statistical risk models lead to explore machine-learning methods. This study evaluates the implementation and performance of a decision tree (CART) and a multilayer perceptron (MLP) to predict cardiovascular risk from real data. The study population was randomly splitted in a learning set (n = 10,296) and a test set (n = 5,148). CART and the MLP were implemented at their best performance on the learning set and applied on the test set and compared to a logistic model. Implementation, explicative and discriminative performance criteria are considered, based on ROC analysis. Areas under ROC curves and their 95% confidence interval are 0.78 (0.75-0.81), 0.78 (0.75-0.80) and 0.76 (0.73-0.79) respectively for logistic regression, MLP and CART. Given their implementation and explicative characteristics, these methods can complement existing statistical models and contribute to the interpretation of risk.

Full text

PDF
156

Selected References

These references are in PubMed. This may not be the complete list of references from this article.

  1. Cooper G. F., Aliferis C. F., Ambrosino R., Aronis J., Buchanan B. G., Caruana R., Fine M. J., Glymour C., Gordon G., Hanusa B. H. An evaluation of machine-learning methods for predicting pneumonia mortality. Artif Intell Med. 1997 Feb;9(2):107–138. doi: 10.1016/s0933-3657(96)00367-3. [DOI] [PubMed] [Google Scholar]
  2. Grover S. A., Paquet S., Levinton C., Coupal L., Zowall H. Estimating the benefits of modifying risk factors of cardiovascular disease: a comparison of primary vs secondary prevention. Arch Intern Med. 1998 Mar 23;158(6):655–662. doi: 10.1001/archinte.158.6.655. [DOI] [PubMed] [Google Scholar]
  3. Gueyffier F., Boutitie F., Boissel J. P., Coope J., Cutler J., Ekbom T., Fagard R., Friedman L., Perry H. M., Pocock S. INDANA: a meta-analysis on individual patient data in hypertension. Protocol and preliminary results. Therapie. 1995 Jul-Aug;50(4):353–362. [PubMed] [Google Scholar]
  4. Hanley J. A., McNeil B. J. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology. 1982 Apr;143(1):29–36. doi: 10.1148/radiology.143.1.7063747. [DOI] [PubMed] [Google Scholar]
  5. Harrell F. E., Jr, Lee K. L., Mark D. B. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat Med. 1996 Feb 28;15(4):361–387. doi: 10.1002/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4. [DOI] [PubMed] [Google Scholar]
  6. Irwig L., Tosteson A. N., Gatsonis C., Lau J., Colditz G., Chalmers T. C., Mosteller F. Guidelines for meta-analyses evaluating diagnostic tests. Ann Intern Med. 1994 Apr 15;120(8):667–676. doi: 10.7326/0003-4819-120-8-199404150-00008. [DOI] [PubMed] [Google Scholar]
  7. Jackson R., Barham P., Bills J., Birch T., McLennan L., MacMahon S., Maling T. Management of raised blood pressure in New Zealand: a discussion document. BMJ. 1993 Jul 10;307(6896):107–110. doi: 10.1136/bmj.307.6896.107. [DOI] [PMC free article] [PubMed] [Google Scholar]
  8. Justice A. C., Covinsky K. E., Berlin J. A. Assessing the generalizability of prognostic information. Ann Intern Med. 1999 Mar 16;130(6):515–524. doi: 10.7326/0003-4819-130-6-199903160-00016. [DOI] [PubMed] [Google Scholar]
  9. Knuiman M. W., Vu H. T., Segal M. R. An empirical comparison of multivariable methods for estimating risk of death from coronary heart disease. J Cardiovasc Risk. 1997 Apr;4(2):127–134. [PubMed] [Google Scholar]
  10. Lapuerta P., Azen S. P., LaBree L. Use of neural networks in predicting the risk of coronary artery disease. Comput Biomed Res. 1995 Feb;28(1):38–52. doi: 10.1006/cbmr.1995.1004. [DOI] [PubMed] [Google Scholar]
  11. Raubertas R. F., Rodewald L. E., Humiston S. G., Szilagyi P. G. ROC curves for classification trees. Med Decis Making. 1994 Apr-Jun;14(2):169–174. doi: 10.1177/0272989X9401400209. [DOI] [PubMed] [Google Scholar]
  12. Unwin N., Thomson R., O'Byrne A. M., Laker M., Armstrong H. Implications of applying widely accepted cholesterol screening and management guidelines to a British adult population: cross sectional study of cardiovascular disease and risk factors. BMJ. 1998 Oct 24;317(7166):1125–1130. doi: 10.1136/bmj.317.7166.1125. [DOI] [PMC free article] [PubMed] [Google Scholar]

Articles from Proceedings of the AMIA Symposium are provided here courtesy of American Medical Informatics Association

RESOURCES