Your browser doesn't support javascript.
loading
Predicting metastasis in breast cancer: comparing a decision tree with domain experts.
Razavi, Amir R; Gill, Hans; Ahlfeldt, Hans; Shahsavar, Nosrat.
Afiliación
  • Razavi AR; Department of Biomedical Engineering, Division of Medical Informatics, Linköping University, University Hospital, S-58185 Linköping, Sweden. amirreza.razavi@imt.liu.se
J Med Syst ; 31(4): 263-73, 2007 Aug.
Article en En | MEDLINE | ID: mdl-17685150
ABSTRACT
Breast malignancy is the second most common cause of cancer death among women in Western countries. Identifying high-risk patients is vital in order to provide them with specialized treatment. In some situations, such as when access to experienced oncologists is not possible, decision support methods can be helpful in predicting the recurrence of cancer. Three thousand six hundred ninety-nine breast cancer patients admitted in south-east Sweden from 1986 to 1995 were studied. A decision tree was trained with all patients except for 100 cases and tested with those 100 cases. Two domain experts were asked for their opinions about the probability of recurrence of a certain outcome for these 100 patients. ROC curves, area under the ROC curves, and calibration for predictions were computed and compared. After comparing the predictions from a model built by data mining with predictions made by two domain experts, no significant differences were noted. In situations where experienced oncologists are not available, predictive models created with data mining techniques can be used to support physicians in decision making with acceptable accuracy.
Asunto(s)
Buscar en Google
Bases de datos: MEDLINE Asunto principal: Neoplasias de la Mama / Árboles de Decisión / Sistema de Registros / Metástasis de la Neoplasia Tipo de estudio: Health_economic_evaluation / Prognostic_studies / Risk_factors_studies Límite: Female / Humans País/Región como asunto: Europa Idioma: En Revista: J Med Syst Año: 2007 Tipo del documento: Article País de afiliación: Suecia
Buscar en Google
Bases de datos: MEDLINE Asunto principal: Neoplasias de la Mama / Árboles de Decisión / Sistema de Registros / Metástasis de la Neoplasia Tipo de estudio: Health_economic_evaluation / Prognostic_studies / Risk_factors_studies Límite: Female / Humans País/Región como asunto: Europa Idioma: En Revista: J Med Syst Año: 2007 Tipo del documento: Article País de afiliación: Suecia