Resumen

CASTRILLON, Omar D.; CASTANO, Eduardo  y  CASTILLO, Luis F.. Bayesian Predictive System for Detection of Breast Cancer. Inf. tecnol. [online]. 2018, vol.29, n.3, pp.257-270. ISSN 0718-0764.  http://dx.doi.org/10.4067/S0718-07642018000300257.

We propose a predictive method to detect breast cancer, based on the following variables: Age, weight, height, body mass index, schooling, socioeconomic stratum, social security, smoker, when quit smoking, passive smoker, consumption of liquor, quantity of liquor, family inheritance of cancer, age of menarche, menopause, pregnancies, age of first birth, breastfeeding, consumption of oral contraceptives, how many years of oral contraceptive use, oral contraceptive suspension time, hormone replacement therapy, and the presence of the GSTM1 gene. Taking as reference patients from the central region of Colombia (Caldas), two databases were defined, one of people without cancer and another of people with cancer. The same training database was used for testing. The proposed methodology defines and trains a Bayesian classification system, with a database of patients with cancer and without cancer. Subsequently, a system validation is performed in order to determine the number of successes and errors in the recognition of this disease. As a result, a 100% success rate is achieved.

Palabras clave : bayesian classifier; breast cancer; training; automated disease detection.

        · resumen en Español     · texto en Español     · Español ( pdf )