Osama Hamzeh

 

Date: Monday, July 8, 2019

Time: 12:00 pm - 2:00 pm

Location: 3105, Lambton Tower

 

Identifying biomarkers that can be used to detect or classify certain diseases, or predicting when a disease becomes more aggressive is one of the most important applications of machine learning. We will demonstrate how we extensively used machine learning techniques to identify genes that can be used to predict prostate cancer stages with very high accuracy, using gene expressions. We will also show how we applied machine learning techniques and used copy number variations to predict when bladder cancer patients might move from non-muscle invasive stages to the critical muscle invasive stages. We were also successful in predicting the location of cancer in the prostate based on gene expressions.

We will also propose during this presentation a new method that we can apply to assist machine learning tools with existing literature knowledge that provides proven relationships among diseases and genes. 

The new method provides the best of traditional machine learning techniques with proven biomarkers from the latest published medical findings.

Thesis Committee:

 

PhD Thesis Proposal Announcement