A machine learning model to diagnose Li-Fraumeni syndrome & Predicting emergency department use

4 Views
administrator
administrator
07/05/23

T-CAIREM Trainee Rounds
PRESENTERS: Brianne Laverty and Christopher Noel
DATE: June 13, 2022 (Monday)
VENUE: Zoom
PRESENTERS: Brianne Laverty and Christopher Noel
_______________________

BRIANNE LAVERTY
PhD candidate, Department of Medical Biophysics

TITLE OF TALK: A machine learning model to diagnose Li-Fraumeni syndrome from the tumour genome.

ABSTRACT: Many institutions worldwide have implemented large-scale tumour sequencing programs to deliver personalized treatment. We hypothesized that individuals with cancer predispositions developed unique tumours genomes. We created a machine-learning model that used tumour whole genome sequencing data to identify individuals with Li-Fraumeni syndrome, a hereditary cancer predisposition syndrome caused by germline TP53 mutations. Diagnosis of Li-Fraumeni syndrome allows individuals to enter a surveillance program for early detection of secondary tumours, leading to higher survival rates.

BIOGRAPHY: Brianne Laverty is a second-year PhD student in computational genomics at the University of Toronto. She completed her Bachelor of Science in mathematics and biology at McMaster University. Laverty enjoys using the logical structure of mathematics to understand complex biological problems. She is currently in Dr. David Malkinโ€™s lab studying the germline somatic interaction in the context of Li-Fraumeni syndrome.
--------------

CHRISTOPHER NOEL, MD, PhD
PGY3 Resident Physician

TITLE OF TALK: Predicting emergency department use and unplanned hospitalization in patients with head and neck cancer: Development and validation of a machine learning algorithm

ABSTRACT: Reducing emergency department (ED) use is important for both patients and heath care systems. Using data from over 70,000 outpatient encounters in Ontario, we developed a machine learning algorithm that can accurately predict future ED use in patients with head and neck cancer. The algorithm has high discrimination and calibration and may help direct targeted intervention.

BIOGRAPHY: Dr. Noel is a PGY-3 resident in the Department of Otolaryngology-Head and Neck Surgery at the University of Toronto. He received his MD from the University of Toronto in 2016. From 2019 to 2022, he stepped out of residency to complete a PhD in Clinical Epidemiology and Health Care Research. His doctoral work centred on enhancing Cancer Care Ontarioโ€™s standardized symptom assessment care pathways. He has an established research track record with over 60 peer reviewed publications and more than $1.5 million in scholarships and grant funding. His work has been published in several leading medical journals including the Journal of Clinical Oncology, JAMA Oncology, JNCCN, and Cancer.

Show more

0 Comments Sort By

No comments found

Facebook Comments

Up next