FUZZY DECISION TREE LEARNING FOR PREOPERATIVE CLASSIFICATION OF ADNEXAL MASSES

Emad Ahmadi, Hoda Javadi, Amin Khansefid, Atousa Asadi, Mohammad Mehdi Ebadzadeh, Dirk Timmerman

2011

Abstract

The study problem was learning a fuzzy decision tree to classify patients with adnexal mass into either of benign or malignant class prior to surgery using patients’ medical history, physical exam, laboratory tests, and ultrasonography. A learning algorithm was developed to learn a fuzzy decision tree in three steps. In the growing step, a binary decision tree was learned from a dataset of patients while fuzzy discretization was used in decision nodes testing continuous attributes. The best degree of fuzziness was automatically found by an algorithm based on optimization procedures. In the pruning step, the overfitted nodes were removed by an algorithm based on critical value post-pruning method. In the refitting step, the labels of the leaf nodes were optimized. The final resulted tree had 10 decision nodes and 11 leaf nodes. Performance testing of the tree gave AUC of ROC of 0.91 and mean squared error of 0.1. The tree was translated into a set of 11 fuzzy if-then rules and the clinical plausibility of the rules was assessed by domain experts. All rules were verified to be in agreement with medical knowledge in the domain. Despite the small learning set and the lack of some important input variables, this method gave accurate and, more importantly, clinically interpretable results.

References

  1. Hoffman, M. S. 2009. Overview of the evaluation and management of adnexal masses. In: mann, W. J. & goff, B. (eds.) Uptodate. 17.3 ed. Waltham: uptodate inc.
  2. Mann, W. J., chalas, e. & Valea, F. A. 2009. Epithelial ovarian cancer: initial surgical management. In: goff, b. (ed.) Uptodate. 17.3 ed. Waltham: uptodate inc.
  3. Mingers, J. 1989. An empirical comparison of pruning methods for decision tree induction. Mach learn, 4, 227-43.
  4. Mitchell, T. M. 1997. Decision tree learning. In: Mitchell, T. M. (ed.) Machine learning. 1st ed. Columbus: mcgraw-hill.
  5. Myers, E. R., bastian, L. A., Havrilesky, L. J., Kulasingam, S. L., Terplan, M. S., Cline, K. E., Gray, R. N. & Mccrory, D. C. Management of Adnexal Mass. Evidence report/technology assessment no.130 (prepared by the duke evidence-based practice center under contract no. 290-02-0025.) Ahrq publication no. 06-e004. Rockville, md: agency for healthcare research and quality. Feb 2006.
  6. Olaru, C. & Louis, W. 2003. A complete fuzzy decision tree technique. Fuzzy set syst, 138, 221-54.
  7. Schaffer, J. I. 2008. Epithelial ovarian cancer. In: schorge, J. O., schaffer, J. I., halvorson, L. M., hoffman, B. L., bradshaw, K. D. & cunningham, F. G. (eds.) Williams gynecology. 1st ed. Dallas: mcgraw-hill.
  8. Timmerman, D., Valentin, L., Bourne, T. H., collins, W. P., Verrelst, H. & Vergote, I. 2000. Terms, definitions and measurements to describe the sonographic features of adnexal tumors: a consensus opinion from the international ovarian tumor analysis (iota) group. Ultrasound obstet gynecol, 16, 500-5.
Download


Paper Citation


in Harvard Style

Ahmadi E., Javadi H., Khansefid A., Asadi A., Mehdi Ebadzadeh M. and Timmerman D. (2011). FUZZY DECISION TREE LEARNING FOR PREOPERATIVE CLASSIFICATION OF ADNEXAL MASSES . In Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2011) ISBN 978-989-8425-34-8, pages 364-375. DOI: 10.5220/0003179703640375


in Bibtex Style

@conference{healthinf11,
author={Emad Ahmadi and Hoda Javadi and Amin Khansefid and Atousa Asadi and Mohammad Mehdi Ebadzadeh and Dirk Timmerman},
title={FUZZY DECISION TREE LEARNING FOR PREOPERATIVE CLASSIFICATION OF ADNEXAL MASSES},
booktitle={Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2011)},
year={2011},
pages={364-375},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003179703640375},
isbn={978-989-8425-34-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2011)
TI - FUZZY DECISION TREE LEARNING FOR PREOPERATIVE CLASSIFICATION OF ADNEXAL MASSES
SN - 978-989-8425-34-8
AU - Ahmadi E.
AU - Javadi H.
AU - Khansefid A.
AU - Asadi A.
AU - Mehdi Ebadzadeh M.
AU - Timmerman D.
PY - 2011
SP - 364
EP - 375
DO - 10.5220/0003179703640375