You are here
Dr. Aline Talhouk
Obstetrics & Gynecology
Faculty of Medicine
Dr. Talhouk is an assistant professor in the department of Obstetrics & Gynecology in the Faculty of Medicine at the University of British Columbia. She is also the director of data science and informatics at OVCARE, BC’s ovarian and gynecological cancer research program. She completed her PhD in Statistics at the University of British Columbia in 2013 with a focus on computational statistics and machine learning. Since then, she has been working on developing and implementing predictive models to improve patient care in women’s health and oncology. Her research focus also includes the ethics of data sharing and privacy in the era of digital health and AI modeling.
Dr. Talhouk's current research program proposes to bring individualized care to endometrial cancer patients by using genetic characteristics of the cancer, as well as other data and risk factors, to predict which women are at higher risk of getting endometrial cancer, or having recurrent disease, and directing them to the appropriate prevention strategy and therapeutic options. Dr. Talhouk is also researching the ethical use of innovative tools in digital health and informatics, including mobile health data and data from wearables. She is collaborating with researchers from computer science to build infrastructure that uses privacy preserving artificial intelligence and machine learning to derive predictive analytics that empower patients, without compromising their privacy.
She is a member of the Ovarian Tumour Tissue Analysis consortium and the Cascadia Data Discovery Initiative.
"Precision Medicine To Drive Prevention And Management Strategies For Women With Endometrial Cancer"
Endometrial cancer (EC), or cancer of the uterus, is the most common gynecological cancer in Canada, with new cases and deaths increasing annually, due to an increase in the rate of common risk factors, like obesity. In British Columbia, the number of new EC cases is projected to increase by 50% and mortality to double by 2031. We must investigate economically feasible prevention strategies to control the rate of this cancer.
For women diagnosed with EC, it is difficult for clinicians to reliably distinguish between cancers that can be cured and those likely to progress, because parameters currently used to make this judgement are not reliably measured. Consequently, we give toxic treatment (chemotherapy and radiation) to many patients who may only require surgery, and fail to treat others as aggressively as we should.
My research program adopts a precision medicine approach, defined by the individualized care to EC patients, to predict:
1. which patients are at high risk of developing EC, and
2. and of those, which patients are likely to progress. Precision medicine can also improve early screening efforts to reduce EC incidence by detecting and treating pre-cancers, promoting early improved diagnosis, and targeting treatment recommendations for EC patients. This will benefit both patients and the healthcare system, as fewer EC patients will be given expensive toxic cancer treatments that are not needed, or to which they are unlikely to respond.
Digital Health, Machine Learning, Diagnostic Models, Prevention, Personalized Medicine, Privacy, Computer Science and Statistics, Epidemiology, Bioinformatics, Cancer of the Reproductive System