期刊
HEALTH INFORMATION SCIENCE AND SYSTEMS
卷 7, 期 1, 页码 -出版社
SPRINGER
DOI: 10.1007/s13755-019-0082-4
关键词
Missing data; Imputation; Classification; Breast cancer; Post-treatment amenorrhoea
资金
- Melbourne Research Scholarships (MRS) [385545]
- Fertility After Cancer Predictor (FoRECAsT) Study
- MDHS Fellowship, University of Melbourne
- FoRECAsT consortium
- Victorian Government through a Victorian Cancer Agency (Early Career Seed Grant)
Clinical decision support using data mining techniques offers more intelligent way to reduce the decision error in the last few years. However, clinical datasets often suffer from high missingness, which adversely impacts the quality of modelling if handled improperly. Imputing missing values provides an opportunity to resolve the issue. Conventional imputation methods adopt simple statistical analysis, such as mean imputation or discarding missing cases, which have many limitations and thus degrade the performance of learning. This study examines a series of machine learning based imputation methods and suggests an efficient approach to in preparing a good quality breast cancer (BC) dataset, to find the relationship between BC treatment and chemotherapy-related amenorrhoea, where the performance is evaluated with the accuracy of the prediction. To this end, the reliability and robustness of six well-known imputation methods are evaluated. Our results show that imputation leads to a significant boost in the classification performance compared to the model prediction based on listwise deletion. Furthermore, the results reveal that most methods gain strong robustness and discriminant power even the dataset experiences high missing rate (> 50%).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据