Comparison of Fuzzy Inference, Logistic Regression, and Classification Trees (CART)

Summary

Objectives: In this paper three statistical methods [logistic regression, classification and regression tree (CART), and fuzzy inference] for the prediction of lymph node metastasis in carcinoma of the tongue are compared. Methods: A retrospective collection of data in 75 patients treated for tongue cancer was carried out at the Clinic and Policlinic for Oral and Maxillo-facial Surgery at the University Hospital of Freiburg in Germany between January 1990 and December 1999; biopsy material was used for laboratory evaluations. Statistical methods for the prediction of lymph node metastasis were compared using ROC curves and accuracy rates. Results: All three methods show similar results for the prediction of lymph node metastasis with slightly superior results for fuzzy inference and CART. A great overlap is apparent in the ROC curves. The best result observed for fuzzy inference and CART was a sensitivity of 79.2% [95% confidence interval: (57.8%; 92.9%)] and a specificity of 86.3% (73.7%; 94.3%); the best result for predictions based on the logistic regression was a sensitivity of 66.7% (44.7%; 84.4%) and a specificity of 80.4% (66.9%; 90.2%). Accuracy rates of fuzzy method and CART were higher [accuracy rate for fuzzy method and CART: 84% (73.7%; 91.4%), for logistic regression method: 73.3%, 95%-CI: (61.9%; 82.9%)]. Conclusions: From a clinical point of view, the predictive ability of the three methods is not sufficiently large to justify use of these methods in daily practice. Other factors probably on the molecular level are needed for the prediction of lymph node metastasis.

Keywords

Tongue cancer - prediction of metastasis - logistic regression - classification and regression tree - fuzzy inference

• Reference

• 1 Strong EW, Kasdorf H, Henk JM. Squamous cell carcinoma of the head and neck. In: Hermanek P, Gospodarowicz MK, Henson DE, Hutter RVP, Sobin LH. Prognostic Factors in Cancer. Berlin – Heidelberg – New York: Springer; 1995
• 2 Magnano M, Bongioannini G, Lerda W. et al. Lymphnode metastasis in head and neck squamous cells carcinoma: multivariate analysis of prognostic variables. J Exp Clin Cancer Res 1999; 18: 79-83.
• 3 Kurokawa H, Yamashita Y, Takeda S, Zhang M, Fukuyama H, Takahashi T. Risk factors for late cervical lymph node metastases in patients with stage I or II carcinoma of the tongue. Head Neck 2002; 24: 731-6.
• 4 Nagata T, Ozeki S, Ohishi M, Arita S. Predicition of cervical lymph node metastasis in carcinoma of the tongue using fuzzy inference. Biomedical Soft Computing and Human Sciences 2000; 6: 51-9.
• 5 Cox DR, Snell EJ. The analysis of binary data (2nd edition). London: Chapman & Hall/CRC; 1989
• 6 Hosmer DW, Lemeshow S. Applied logistic regression. New York: John Wiley & Sons, Inc.; 1989
• 7 Sauerbrei W, Royston P. Building multivariable prognostic and diagnostic models: transformation of the predictors using fractional polynomials. Journal of the Royal Statistical Society, Series A 1999; 162: 71-94.
• 8 Sauerbrei W. The use of resampling methods to simplify regression models in medical statistics. Applied Statistics 1999; 48: 313-29.
• 9 Breiman L, Friedman JH, Olsen RA, Stone CJ. Classification and regression trees. Monterey: Wadesworth, Inc.; 1984
• 10 Lausen B, Sauerbrei W, Schumacher M. Classification and Regression Trees (CART) used for the exploration of prognostic factors measured on different scales. In: Dirschedl P, Oster-mann R. Computational Statistics. Heidelberg: Physica-Verlag; 1994: 483-96.
• 11 Leemis LM, Trivedi KG. A comparison of approximate interval estimators for the Bernoulli parameter. American Statistician 1996; 50: 63-8.
• 12 Hiratsuka H, Miyakawa A, Nakamori K, Kido Y, Sunakawa H, Kohama G. Multivariate analysis of occult lymph node metastasis as a prognostic indicator for patients with squamous cell carcinoma of the oral cavity. Cancer 1997; 80: 351-6.
• 13 Kurokawa H, Yamashita Y, Murata T. et al. Histological grading of malignancy correlates with regional lymph node metastasis and survival of patients with oral squamous cell carcinoma. Fukuoka Acta Med 1998; 89: 225-31.
• 14 Woolgar JA, Scott J. Prediction of cervical lymph node metastasis in squamous cell carcinoma of the tongue/floor of mouth. Head Neck 1995; 17: 463-72.
• 15 Lopes MA, Nikitakis NG, Reynolds MA, Ord RA, Sauk J. Biomarkers predictive of lymph node metastases in oral squamous cell carcinoma. J Oral Maxillofac Surg 2002; 60: 142-7.
• 16 Byers RM, El-Naggar AK, Lee YY. et al. Can we detect or predict the presence of occult nodal metastases in patients with squamous carcinoma of the oral tongue?. Head Neck 1998; 20: 138-44.
• 17 Okamoto M, Nishimine M, Kishi M. et al. Prediction of delayed neck metastasis in patients with stage I/II squamous cell carcinoma of the tongue. J Oral Pathol Med 2002; 31: 227-33.
• 18 Hayashi C. On the prediction of phenomena from qualitative data and the quantification of qualitative data from the mathematico-statistical point of view. Annals of the Institute of Statistical Mathematics 1952; 3: 69-98.
• 19 Schwarzer G, Vach W, Schumacher M. On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology. Stat Med 2000; 19: 541-61.
• 20 Schumacher M, Holländer N, Schwarzer G, Sauerbrei W. Prognostic Factor Studies. In: Crowley J. Handbook of Statistics in Clinical Oncology. Marcel Dekker, Inc.; 2001: 321-78.
• 21 Giacomarra V, Tirelli G, Papanikolla L, Bussani R. Predictive factors of nodal metastases in oral cavity and oropharynx carcinomas. The Laryngoscope 1999; 109: 795-9.
• 22 Ogura I, Amagasa T, Miyakura T. Correlation between tumor consistency and cervical metastasis in tongue carcinoma. Head Neck 2000; 22: 229-33.
• 23 Simon R, Altman DG. Statistical Aspects of Prognostic Factor Studies in Oncology. British Journal of Cancer 1994; 69: 979-85.