Medical Expert Evaluation of Machine Learning Results for a Coronary Heart Disease Database
- First Online:
A set of machine learning experiments was performed on the atherosclerotic coronary heart disease data collected in the regular med- ical practice, with intention to evaluate established medical diagnostic practice, investigate the relations between the results of less important diagnostic tests, and detect novel regularities in patients’ data. The re- sults of these experiments were evaluated by the medical expert for their soundness with respect to the existing knowledge in the domain, and potential for the generation of new and useful medical knowledge. The performed experiments generally verify the existing medical practice in non-invasive diagnosis of atherosclerotic coronary heart disease, but also demonstrate how the synergy of medical and machine learning expertise helps in the inference of a new knowledge and potentially could increase effciency and reliability of the medical diagnostic process.
Unable to display preview. Download preview PDF.
- 2.Carrault, G., Cordier, M.O., Quiniou, R., Garreau, M., Bellanger, J.J., Bardou, A. (1999) A Model-Based Approach for Learning to Identify Cardiac Arrhythmias. In Proc. of Joint European Conference on Artificial Intelligence in Medicine and Medical Decision Making (AIMDM’99), 165–174. Springer, Berlin.Google Scholar
- 6.Fernandez, E.A., Presedo, J., Barro, S.(1999) An ECG Ischaemic Detection System Based on Self-Organizing Maps and a Sigmoid Function Pre-processing Stage. In Proc. of Joint European Conference on Artificial Intelligence in Medicine and Medical Decision Making (AIMDM’99), 207–216. Springer, Berlin.Google Scholar
- 7.Gamberger, D. (1995). A minimization approach to propositional inductive learning. In Proc. of the 8th European Conference on Machine Learning, 151–160. Springer, Berlin.Google Scholar
- 8.Gerson, C.M. (1987). Test accuracy, test selection and test result interpretation in chronic coronary artery disease. In Gerson, C.M. (ed.) Cardiac Nuclear Medicine, pp. 309–347. McGraw Hill.Google Scholar
- 9.Grošelj, C., Kukar, M., Fetich, J. & Kononenko, I. (1997). Machine learning improves the accuracy of coronary artery disease diagnostic methods. Computers in Cardiology 24: 57–60.Google Scholar
- 10.Kong, D.F., Del Carlo, C.H., Eisenstein, E.L. (1999). Predicting survival in coronary disease: machine-learning computer models versus expert clinicians. European Heart Journal Abstract Supplement 20: 312.Google Scholar
- 11.Torchio, M., Battista, S., Bar, F., Pollet, C., Marzuoli, M., Bucchi, M.C., Pagni, R., Molino, G.(1999) A Decision Support System for the Identification, Staging,and Functional Evaluation of Liver Diseases (HEPASCORE). In Proc. of Joint European Conference on Artificial Intelligence in Medicine and Medical Decision Making (AIMDM’99), 158–164. Springer,Berlin.Google Scholar
- 12.Wayne A.R., Schlant R.C., Fuster V., In HURST’S: The Heart, Arteries and Veins. McGrawc Hill, NY, 1127–1263.Google Scholar