by Cormac Rea
The Data Sciences Institute (DSI) is pleased to announce its 2024 Doctoral Student Fellowship recipients.
The DSI Doctoral Student Fellowship supports multi-disciplinary training and collaborative research in data sciences that include faculty from the University of Toronto and external funding partners. Fellows will engage in exciting research projects with a data sciences focus, developing novel methodologies or applying existing approaches innovatively. Each fellow has at least two co-supervisors from complementary disciplinary backgrounds to guide the multidisciplinary aspects of their research project. In addition to their research, Fellows engage in DSI professional development and data skills programming and networking.
“It is a pleasure to announce the selection of our 14 new fellows for the DSI Doctoral Student Fellowship,” says Laura Rosella, DSI Associate Director of Education and Training.
“Each fellow is an outstanding scholar and we’re excited to see how their research in data sciences can both address important societal questions and drive change. The impact of their work and contributions to the DSI community impacting several sectors of society will be eagerly anticipated by many.”
Optimizing Patient Safety Reporting and Providing Improved Patient Centred Care
Rob (Hongbo) Chen is working with his supervisors, Profs. Myrtede Alfred and Eldan Cohen (University of Toronto, Faculty of Applied Science and Engineering, Department of Mechanical and Industrial Engineering), to focus on research that leverages data science to optimize the efficiency, equity and user-interaction of patient safety event report classification.
Chen, a PhD student with Faculty of Engineering’s Department of Mechanical & Industrial Engineering, recently described his work in an interview with MIE’s digital news.
“Adverse events attributed to patient safety challenges are the third leading cause of death in the world, resulting in 251,454 deaths annually in the United States alone,” says Chen, whose research aims to synthesize human-centered design principles with artificial intelligence (AI) to improve patient safety.
“The possibility of using AI to create more reliable and user-friendly incident reporting systems is a very real solution to the current challenges healthcare professionals face with complex classification taxonomy and the consequences of misclassified incident reports.”
“Accurate classification of patient safety event reports is crucial to analyzing trends, prioritizing measures to reduce such adverse events, and supporting organizational learning,” adds Prof. Cohen.
“Rob is combining state-of-the-art machine learning with human factors engineering principles to build tools that can significantly improve healthcare quality.”
Measuring the public health benefits from Zero Emissions Vehicles
Harshit Gujral, a PhD student in Computer Science (C/S Environment & Health), is working on a research topic that explores the measurement of public health benefits from Zero Emissions Vehicles.
“Transitioning to electric vehicles (EVs) is crucial in reducing our reliance on fossil fuels, but it’s not without its challenges—from disparities in adoption rates to increased non-tailpipe emissions as more vehicles hit the roads,” explains Gujral. “If not managed properly, EV transition can exacerbate existing health disparities, particularly for marginalized communities.”
“My research taps into data science to quantify the health benefits and inequities associated with Zero-Emission Vehicle mandates, advocating for data-driven, evidence-based policies that support a rapid and equitable EV transition,” he says.
“At DSI, I’m excited to engage with experts and policymakers to refine our understanding of the health impacts of the EV transition. Working together, we can ensure our environmental policies do more—not only mitigate environmental harm but also promote health equity.”
Gujral is collaborating with supervisors Profs. Steve Easterbrook (University of Toronto, Faculty of Arts & Science, Department of Computer Science), Meredith Franklin (University of Toronto, Faculty of Arts & Science, Department of Statistical Sciences), and Paul Kushner (University of Toronto, Faculty of Arts & Science, Department of Physics) on his research.
“Harshit will leverage big data and computational skills to tackle an important question at the intersection of climate science and public health — how can zero emission vehicle policies promote an equitable shift to electric vehicle adoption that will benefit public health?” explains Prof. Franklin.
“His results have the potential to have significant impact on how zero emission vehicle policies are effectively implemented in the US and Canada, which in turn could result in substantive impact to our climate and health.”
Congratulations to all the 2024 DSI Doctoral Student Fellows. Learn more about each of them below:
Dorothy Apedaile – Using Machine Learning to Investigate Homelessness and HIV Vulnerability Among Transgender Women in the United States
Supervisors: Amaya Perez-Brumer and Susan Bonday, University of Toronto, Dalla Lana School of Public Health
Samantha Berek – Understanding galaxy evolution using star cluster populations with statistical models
Supervisors: Gwendolyn Eadie, University of Toronto, Faculty of Arts & Science, David A. Dunlap Department of Astronomy and Astrophysics; Joshua Speagle and Monica Alexander, University of Toronto, Faculty of Arts & Science, Department of Statistical Sciences
Duncan Carruthers-Lay – Understanding the fundamental biology of Neisseria gonorrhoeae through an integrated omics approach and metabolic modelling
Supervisors: John Parkinson, The Hospital for Sick Children; Scott Gray-Owen, University of Toronto, Temerty Faculty of Medicine, Department of Molecular Genetics
Hongbo Chen – Leveraging data science approaches to optimize the efficiency, equity, and user-interaction of patient safety event report classification
Supervisors: Myrtede Alfred and Eldan Cohen, University of Toronto, Faculty of Applied Science and Engineering, Department of Mechanical and Industrial Engineering
Chaoran Dong – Estimating the Value of Reducing Geographical Disparities in Pediatric Cancer Care using Health Administrative Data
Supervisors: Petros Pechlivanoglou, University Health Network, Princess Margaret Cancer Centre; Linbo Wang, University of Toronto Scarborough, Department of Computer and Mathematical Sciences
Mei Dong – Advancing Mendelian Randomization Methods for Lung Cancer Research
Supervisors: Wei Xu, The Child Health Evaluative Sciences Hospital for Sick Children; Linbo Wang, University of Toronto Scarborough, Department of Computer and Mathematical Sciences
Harshit Gujral – Towards Equitable ZEV mandates: Measuring the public health benefits from Zero Emissions Vehicles
Supervisors: Steve Easterbrook, University of Toronto, Faculty of Arts & Science, Department of Computer Science; Meredith Franklin, University of Toronto, Faculty of Arts & Science, Department of Statistical Sciences; Paul Kushner, University of Toronto, Faculty of Arts & Science, Department of Physics
Ramaravind Kommiyamothilal – Reducing Online Toxicity through Exposure to Diverse Opinions
Supervisors: Shion Guha, University of Toronto, Faculty of Information; Syed Ishtiaque Ahmed, University of Toronto, Faculty of Arts & Science, Department of Computer Science
Alexander Laroche – Discovering middle-aged massive binaries throughout the Milky Way with deep learning
Supervisors: Joshua Speagle, University of Toronto, Faculty of Arts & Science, Department of Statistical Sciences; Maria Drout, University of Toronto, Faculty of Arts & Science, David A. Dunlap Department of Astronomy and Astrophysics
Eric Sanders – Statistical genetics of sex-dependent phenotypes: Applications in the common genetic epilepsies
Supervisors: Lisa Strug, University of Toronto, Faculty of Arts & Science, Department of Statistical Sciences; Linbo Wang, University of Toronto Scarborough, Department of Computer and Mathematical Sciences
Yixiong Sun – Realistic neuron network modelling to examine network dysfunctions causing memory impairments in Alzheimer’s disease
Supervisors: Kaori Takehara-Nishiuch, University of Toronto, Faculty of Arts & Science, Department of Psychology; Jiannis Taxidis, The Hospital for Sick Children, Neuroscience and Mental Health
Farzan Taj – A Deep Learning Foundation Model for Predicting Responses to Genetic and Chemical Perturbations in Single Cancer Cells
Supervisors: Lincoln Stein, University of Toronto, Temerty Faculty of Medicine, Department of Molecular Genetics; Benjamin Haibe-Kains, University of Toronto, Temerty Faculty of Medicine, Department of Medical Biophysics
Mete Yuksel – Risk roadmap: using genome sequence data and simulation-based inference to identify dangerous viral reservoirs – and predict pandemic risk
Supervisors: Nicole Mideo and Matthew Osmond, University of Toronto, Faculty of Arts & Science, Department of Ecology and Evolutionary Biology
Xindi Zhang – A Deep Learning System Classifies Tumour Origins Using Somatic Mutation Patterns From Circulating Tumour DNA
Supervisors: Lincoln Stein, University of Toronto, Temerty Faculty of Medicine, Department of Molecular Genetics; Trevor Pugh, University Health Network, Princess Margaret Cancer Centre