IQP TS2 Machine Learning in Cancer Detection

Wang, Shiyue; Zou, Tao

Student Work

IQP TS2 Machine Learning in Cancer Detection

Public Deposited

The use of machine learning techniques by developing three predictive models for cancer diagnosis using descriptions of nuclei sampled from breast masses. Algorithms include regularized General Linear Model regression (GLMs), Support Vector Machines (SVMs) with a radial basis function kernel, and single-layer Artificial Neural Networks. The research trains algorithms on data from the evaluation sample before they are used to predict the diagnostic outcome in the validation dataset, and compares the predictions made on the validation datasets with the real-world diagnostic decisions to calculate the accuracy, sensitivity, and specificity of the three models. The research explores the use of averaging and voting ensembles to improve predictive performance and provides a step-by-step guide to developing algorithms using the open-source programming environment. This research uses a straightforward example to demonstrate the theory and practice of machine learning for clinicians and medical researchers. The principals which we demonstrate here can be applied to other complex tasks including natural language processing and image recognition.

This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

Subject

Publisher