Integrating digital pathology with electronic health records for predicting outcomes in heart transplantation

There is a strong risk of rejection after a patient receives a heart transplant which leads to death in 1 in 5 people that receive the transplant. Biopsies are taken frequently to determine if the new heart is rejecting by looking at the piece of tissue under a microscope. A specialist doctor will then make an assessment as to the rejection status. However many doctors do not agree on the diagnosis and therefore on a definitive diagnosis. We will develop automated algorithms that takes in different kinds of data (images of tissues, doctor’s notes, patient history, blood test results) and aid the doctor in make the rejection assessment. These algorithms can also find places on the tissue images that it thinks are causing the rejection. We will measure the RNA and protein levels in these regions to determine the biology of these regions. The goal of this work is to help the doctor in making a definitive diagnosis of heart transplant rejection and understand the biology behind transplant rejection.

Faculty Supervisor:

Amrit Singh

Student:

Partner:

PROOF Centre of Excellence

Discipline:

Life Sciences

Sector:

Health and Related Sciences & Technology; Professional, scientific and technical services

University:

The University of British Columbia

Program: