Preterm birth risk assessed by a new method of classification using selective partial matching
In the United States, 8–12% of all newborns are delivered preterm, i.e., before 37 weeks of gestation. Most existing methods to assess preterm birth are based on risk scoring. These methods are only between 17% and 38% predictive in determining preterm birth. Hence there is need for data mining and knowledge discovery in database for predicting birth outcomes in pregnant women. This paper presents a new approach to classification (diagnosis) using selective partial matching. It is shown that our approach is more stable and, in general, more accurate than the method used so far. Our other result shows that classification based on more specific rules is worse.
KeywordsPreterm birth machine learning knowledge discovery in databases data mining rough set theory rule induction classification of examples system LERS
Unable to display preview. Download preview PDF.
- Booker, L. B., Goldberg, D. E., and Holland, J. F.: Classifier systems and genetic algorithms. In Machine Learning. Paradigms and Methods. Carbonell, J. G. (ed.), The MIT Press (1990) 235–282.Google Scholar
- Chan, C. C. and Grzymala-Busse, J. W.: On the attribute redundancy and the learning programs ID3, PRISM, and LEM2. Department of Computer Science, University of Kansas, TR-91-14 (1991) 20 pp.Google Scholar
- Feldman, W. E. and Wood, B.: The economic impact of high-risk pregnancies. Journal of Health Care Finance 24 (1997) 64–71.Google Scholar
- Grzymala-Busse, J. W. Managing Uncertainty in Expert Systems. Kluwer Academic Publishers (1991).Google Scholar
- Grzymala-Busse, J. W.: LERS—A system for learning from examples based on rough sets. In Intelligent Decision Support. Handbook of Applications and Advances of the Rough Sets Theory. Slowinski, R. (ed.), Kluwer Academic Publishers (1992) 3–18.Google Scholar
- Grzymala-Busse, J. W.: Managing uncertainty in machine learning from examples. Proc. of the Third Intelligent Information Systems Workshop, Wigry, Poland, June 6–11, 1994, 70–84.Google Scholar
- Grzymala-Busse, J. W., and Goodwin, L. K.: Improving prediction of preterm birth using a new classification scheme and rule induction. Proc. of the 18-th Annual Symposium on Computer Applications in Medical Care (SCAMC), Washington, DC, November 5–9, 1994, 730–734.Google Scholar
- Grzymala-Busse, J. W., and Goodwin, L. K.: A comparison of less specific versus more specific rules for preterm birth prediction. Proc. of the First Online Workshop on Soft Computing WSC1 on the Internet, Nagoya University, Japan, Aug. 19–30, 1996, 129–133.Google Scholar
- Holland, J. H., Holyoak K. J., and Nisbett, R. E.: Induction. Processes of Inference, Learning, and Discovery. The MIT Press (1986).Google Scholar
- Michalski, R. S., Mozetic, I., Hong, J. and Lavrac, N.: The AQ15 inductive learning system: An overview and experiments. Department of Computer Science, University of Illinois, Rep. UIUCDCD-R-86-1260 (1986).Google Scholar
- Pawlak, Z.: Rough Sets. Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishers (1991).Google Scholar
- Slowinski, R. and Stefanowski, J.: Handling various types of uncertainty in the rough set approach. Proc of the RKSD-93, International Workshop on Rough Sets and Knowledge Discovery (1993) 395–397.Google Scholar