Abstract
A stimulus-response LCS, called EpiCS, based upon the BOOLE and NEWBOOLE paradigms, was developed to work in single-step environments in which the goal is to generalize clinical decision rules from medical data by means of building explanatory and predictive models. This paper addresses the scalability of EpiCS to a large database, the Fatal Accident Reporting System (FARS), which is a large prospective database supported by the National Highway Traffic Safety Administration (NHTSA) of Transportation. This investigation used 1998 FARS data, the most recent complete year’s data available at this time. The performance of EpiCS in building explanatory and predictive models compared very favorably with a decision tree inducer and logistic regression applied to these tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Abe, N. and Mamitsuka, H.: Query learning strategies using boosting and bagging. In: Shavlik, J. (ed.): Machine Learning. Proceedings of the Fifteenth International Conference (ICML’98). San Francisco, Morgan Kaufmann Publishers (1998) 1–9.
Bonelli, P., Parodi, A., Sen, S., and Wilson, S.: NEWBOOLE: A fast GBML system, in: Porter, B. and Mooney, R. (eds.), Machine Learning: Proceedings of the Seventh International Conference. Morgan Kaufmann, San Mateo, CA (1990) 153–159.
Catral, R., Oppacher, F. and Duego, D.: Rule acquisition with a genetic algorithm. In Banzhaf, W., Daida, J., Eiben, A.E., et al (eds.): Proceedings of the Genetic and Evolutionary Computation Conference GECCO 99. Morgan Kaufmann, San Francisco (1999), 778.
Harries, M.: Boosting a strong learner: evidence against the minimum margin. In: Bratko, I. and Dzeroski, S. (eds.): Machine Learning. Proceedings of the Sixteenth International Conference (ICML’ 99). Morgan Kaufmann Publishers, San Francisco (1999) 171–180.
Holmes, J.H.: A genetics-based machine learning approach to knowledge discovery in clinical data, Journal of the American Medical Informatics Association Suppl (1996) 883.
Holmes, J.H.: Discovery of Disease Risk with a Learning Classifier System, in: Baeck, T. (ed.): Proceedings of the Seventh International Conference on Genetic Algorithms (SanFrancisco, Morgan Kaufmann (1997) 426–433.
Holmes J.H.: Quantitative methods for evaluating learning classifier system performance In forced two-choice decision tasks. In: Wu, A. (ed.) Proceedings of the Second International Workshop on Learning Classifier Systems (IWLCS99). Morgan Kaufmann, SanFrancisco (1999) 250–257.
Holmes JH, Durbin DR, Winston FK: The Learning Classifier System: An evolutionary computation approach to knowledge discovery in epidemiologic surveillance. Artificial Intelligence in Medicine 19(1): 53–74 (2000).
Holmes JH, Durbin DR, Winston FK: A new bootstrapping method to improve classification performance in learning classifier systems. Schoenauer M, Deb K, Rudolph G, et al (eds.): Parallel Problem Solving from Nature-PPSN VI, Proceedings of The Sixth International Conference: 745–754, 2000.
Marmelstein, R.E. and Lamont, G.: Pattern classification using a hybrid genetic programdecision tree approach. In: Koza J.R., Banzhaf W., Chellapilla K., et al (eds.): Genetic Programming 1998: Proceedings of the Third Annual Conference, Morgan Kaufmann, San Francisco (1998) 223–231.
McNeil, BJ; Hanley, JA. Statistical approaches to the analysis of receiver operating characteristic (ROC) curves. Medical Decision Making. 1984; 4:137–150.
Ngan, P.S., Wong, M.L., Leung, K.S., and Cheng, J.C.Y.: Using grammar-based genetic programming for data mining of medical knowledge. In: Koza J.R., Banzhaf W., Chellapilla K., et al (eds.): Genetic Programming 1998: Proceedings of the Third Annual Conference, Morgan Kaufmann, San Francisco (1998) 254–259.
Quinlan, J.R.: See5: Release 1.13, 2000.
Saxon, S. and Barry, A. XCS and the Monk’s Problem. In Banzhaf, W., Daida, J., Eiben, A.E., et al (eds.): Proceedings of the Genetic and Evolutionary Computation Conference GECCO 99. Morgan Kaufmann, San Francisco (1999), 809.
Schapire, R.E.: Theoretical views of boosting. In: Computational Learning Theory, 4th European Conference, EuroCOLT’99. Springer-Verlag, Berlin (1999) 1–10.
Wilson, S.W., “Get real! XCS with continuous-valued inputs” In Booker, L., Forrest, S., Mitchell, M., and Riolo, R. (eds.): Festschrift in Honor of John H. Holland, May 15–18, 1999 (pp. 111–121),. Center for the Study of Complex Systems, The University of Michigan, Ann Arbor, MI.
Wilson, S.W.: Mining oblique data with XCS. To appear in Lanzi, P. L., Stolzmann, W., and S. W. Wilson (Eds.), Advances in Learning Classifier Systems. Third International Workshop (IWLCS-2000), Lecture Notes in Artificial Intelligence (LNAI-1996). Berlin: Springer-Verlag (2001).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Holmes, J.H. (2001). Applying a Learning Classifier System to Mining Explanatory and Predictive Models from a Large Clinical Database. In: Luca Lanzi, P., Stolzmann, W., Wilson, S.W. (eds) Advances in Learning Classifier Systems. IWLCS 2000. Lecture Notes in Computer Science(), vol 1996. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44640-0_8
Download citation
DOI: https://doi.org/10.1007/3-540-44640-0_8
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42437-6
Online ISBN: 978-3-540-44640-8
eBook Packages: Springer Book Archive