Purging False Negatives in Cancer Diagnosis Using Incremental Active Learning
Authors
Abstract
Cancer is becoming a human plague, and decision-support tools to help physicians better diagnosing are a fulsome research field. False negatives can be a huge problem for cancer diagnosticians, since while a false positive can result in time and money lost, a false negative can result in the lost of human lives, which puts an overwhelming burden on diagnosis.In this framework, we propose a two-fold approach to purge false negatives in cancer diagnosis without compromising precision performance. First, we use an incremental background knowledge method and then, an active learning strategy completes the procedure. The defined incremental active learning SVM method was tested in the
Wisconsin-Madison breast cancer diagnosis problem showing the effectiveness of such techniques in supporting cancer diagnosis.