Stage-specific predictive models for breast cancer survivability
نویسندگان
چکیده
BACKGROUND Survivability rates vary widely among various stages of breast cancer. Although machine learning models built in past to predict breast cancer survivability were given stage as one of the features, they were not trained or evaluated separately for each stage. OBJECTIVE To investigate whether there are differences in performance of machine learning models trained and evaluated across different stages for predicting breast cancer survivability. METHODS Using three different machine learning methods we built models to predict breast cancer survivability separately for each stage and compared them with the traditional joint models built for all the stages. We also evaluated the models separately for each stage and together for all the stages. RESULTS AND CONCLUSIONS Our results show that the most suitable model to predict survivability for a specific stage is the model trained for that particular stage. In our experiments, using additional examples of other stages during training did not help, in fact, it made it worse in some cases. The most important features for predicting survivability were also found to be different for different stages. By evaluating the models separately on different stages we found that the performance widely varied across them. We also demonstrate that evaluating predictive models for survivability on all the stages together, as was done in the past, is misleading because it overestimates performance.
منابع مشابه
Extracting Predictor Variables to Construct Breast Cancer Survivability Model with Class Imbalance Problem
Application of data mining methods as a decision support system has a great benefit to predict survival of new patients. It also has a great potential for health researchers to investigate the relationship between risk factors and cancer survival. But due to the imbalanced nature of datasets associated with breast cancer survival, the accuracy of survival prognosis models is a challenging issue...
متن کاملDevelopment of an Ensemble Multi-stage Machine for Prediction of Breast Cancer Survivability
Prediction of cancer survivability using machine learning techniques has become a popular approach in recent years. In this regard, an important issue is that preparation of some features may need conducting difficult and costly experiments while these features have less significant impacts on the final decision and can be ignored from the feature set. Therefore, developing a machine for p...
متن کاملUtility Estimation of Health Status of Cancer Patients by Mapping for Cost-Utility Analysis
Background: It is important to obtain accurate information about the preferences of people for measuring quality-adjusted life years (QALYs), because it is necessary for cost-utility analysis. In this regard, mapping is a method to access this information. Therefore, the purpose of this study was to map Functional Assessment of Cancer Therapy – General (FACT-G) onto Short Form Six Dimension (SF...
متن کاملOptimal Data Mining Method for Predicting Breast Cancer Survivability
Breast cancer is one of leading causes of death. This study predicts 5-year survivability of breast cancer patients by two data mining techniques. The data set consisted of information about patients who have cancer diagnosis collected by SEER. In this study, data set is pre-classified into survival and non-survival with 90.66% and 9.34%, respectively. The selected variables used to predict 5-y...
متن کاملHealth education models application by peer group for improving breast cancer screening among Iranian women with a family history of breast cancer: A randomized control trial
Background: Studies have shown that participation of Iranian women with family history of breast cancer in screening service is low. This investigation has evaluated the effectiveness of health models according to peer group in improving clinical breast exam (CBE) among Iranian women with a family history of breast cancer. Methods: This was a randomized control ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- International journal of medical informatics
دوره 97 شماره
صفحات -
تاریخ انتشار 2017