| Summary: | 碩士 === 國立雲林科技大學 === 工業工程與管理研究所碩士班 === 100 === abstract
In recent years, the incidence and mortality of breast cancer in Taiwan has continued to rise. The major concern of breast cancer patients after treatment is cancer recurrence. After cancer treatment, the body and mind can be exhausted and such recurrence will result in more damage. Therefore, the first choice of treatment needs to be taken with caution. Physicians and patients need to know the details of different treatment modalities and recurrence rates so that both parties and physiciants can make the best decisions.
This study is to apply data mining to construct the predictive model in breast cancer. The data were collected from the Cancer Registry Database of breast cancer patients, and ananyzed by data mining, decision tree C5.0, backpropagation neural, support vector machine, and ENSEMBLE to predict breast cancer recurrence. The results show that the accuracy of the prediction model were higher than 80%. When combined with backpropagation neural, ENSEMBLE had the highest accuracy rate of 86%, compared to a single backpropagation neural. These results indicate the feasibility of the model’s accuracy and can be a useful diagnostic aid reference for physicians and breast cancer patients.
|
|---|
