Data Science Interdisciplinary Research Cluster

 

DLSPH Data Science Interdisciplinary Research Cluster Funded Projects

 

In the fall of 2020 and 2021, we announced a Seed Funding Call for Proposals for DLSPH faculty to apply for seed funding to support novel data science research to advance population health and health systems. Following adjudication from an interdisciplinary review committee, nine new teams of researchers from DLSPH and affiliate institutions were each awarded $20,000 in seed funding. The Cluster has supported seven projects, and two projects – with a focus on child health – were funded through a generous partnership with the Edwin S.H. Leong Centre for Healthy Children.

In fall of 2022, we began a new collaboration with the Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM) to provide a new research funding opportunity to support the implementation of AI applications that will enhance population health and health systems. Together, with T-CAIREM, we awarded $150,000 grant to support one interdisciplinary project over the next two years in pursuit of this goal.

Congratulations to the 2023-2024 Team:

 

Artificial intelligence decision support tool to assess the quality of systematic reviews on the same topic

PI: Andrea Tricco (DLSPH) 

Co-PIs: Ebrahim Bagheri (UofT), Salmaan Kanji* (The Ottawa Research Institute), Carole Lunny* (St. Michael’s Hospital), Beverley Shea (The Ottawa Research Institute), Areti-Angeliki Veroniki* (IHPME)

Collaborators: Yuan Chi* (Yealth Technology), Maureen Dobbins (McMaster University), Nicola Ferri* (Università di Bologna), Candyce Hamel (Canadian Association of Radiologists), Brian Hutton (The Ottawa Research Institute), Sarah Neil-Sztramko (McMaster University), Ba’ Pham (St. Michael’s Hospital), Dawid Pieper (Center for Health Services), Emma Reid (Nova Scotia Health), Adrienne Stevens (PHAC), Sharon Straus (UofT), Jennifer Watt (St. Michael’s Hospital), Sera Whitelaw* (McGill University), Janet Zhang* (University of British Columbia)

Project description: Decision makers need access to high-quality studies to determine which interventions and policies should be used. Systematic reviews (SRs) are used to summarize all medical literature on a given topic. To manually assess the quality of SRs, two tools are currently used: AMSTAR and ROBIS. However, there is currently no automated tool to quality appraise SRs.

Our project, WISEST (Which Systematic Evidence Synthesis is best), addresses this gap by using items from the AMSTAR and ROBIS tools as features (quality indicators) in our models. WISEST will also use methods features and SR results to help users compare SRs on the same topic. WISEST will transparently provide the rationale behind the AI’s comparison of features, choice of the best SR(s) and allow them to make their own decision based on the AI’s output.

Congratulations to the 2022-2023 Teams:

 

Improving Delivery of Palliative Homecare Services in Ontario with Machine Learning (ML)

Co-PIs: Emily Seto, Marya Zaidi* (DLSPH)

Collaborators: Elham Dolatabadi (Vector/IHPME), Peter Tanuseputro (University of Ottawa)

Project description: Palliative care enables proper pain and symptom management and improved quality of life for those nearing end-of-life (EOL). Unfortunately, only a minority of people who would benefit from palliative care receive these services. Publicly funded palliative homecare reduces acute care usage and improves quality of life for those nearing EOL. This project brings together an interdisciplinary team to explore the use of machine learning (ML) to improve health services for the palliative homecare population. This project will be the first to use routinely collected patient data to build ML models for timely identification of palliative homecare patients in Ontario. Application of the model will identify patients requiring palliative care, thus enabling patients, providers, and families better planning for EOL care.

Reducing SARS-Cov-2 Risk in Children: Using Machine Learning to Improve the ‘Swiss Cheese Model’ of Pandemic Defense

Co-PIs: John Maguire, Mary Alipay* (DLSPH)

Collaborators: Jeff Kwong (DLSPH), Rahul Krishnan (Department of Computer Science, UofT), Charles Keowan-Stoneman (DLSPH Biostatistics), Ashleigh Tuite (DSLPH), Muhammad Mamdani (IHPME)               

Project Description: Over 83,000 children in Ontario have tested positive for SARS-CoV-2. Infection has been associated with increased hospitalizations in children with little data on long-term morbidity. The ‘Swiss Cheese’ model of pandemic defense is an approach to preventing SARS-CoV-2 infection by layering protections, including individual interventions (e.g., handwashing, wearing masks) and community interventions (e.g., school closures, lockdowns). While some layers may provide more protection than others, there are differing costs to children and families associated with each individual intervention. Nearly 2 years into the pandemic, it remains unknown which individual and community interventions are the most effective for preventing infection among children. Using linked cohort (TARGet Kids!) and administrative (ICES) data, this team will use advanced machine learning techniques to determine the most effective interventions for preventing SARS-Cov-2 infection among children. Results will offer parents and policymakers with the evidence needed to balance the benefits of interventions against the costs to families.

Project funded by the Edwin S.H. Leong Centre for Healthy Children.

Migraines and air pollution: Validating the use of migraine smartphone app records compared to emergency room discharge data for environmental exposures and transient health outcomes

Co-PIs: Peter Smith, Andrea Portt* (DLSPH)           

Collaborators: Hong Chen (Public Health Ontario, DLSPH), Antonio Gasparrini (London School of Hygiene & Tropical Medicine), Erjia Ge (DLSPH Biostatistics), Christine Lay (Women’s College Hospital)

Project Description: Migraine causes debilitating head pain, nausea, and sensitivity to light and/or sound for more than 1 billion people worldwide. Migraine drugs can be expensive and under-prescribed, and sometimes have side effects, which leaves many people reliant upon avoiding triggers (e.g. flashing lights, foods, or odours) to avoid migraine attacks. Some research suggests that air pollution such as particulate matter (PM2.5), ozone (O3), and nitrogen dioxide (NO2) may cause migraine attacks. The majority of the research used clinic and hospital records. These include imprecise attack start times, so it is hard to know which of the many air pollutants we breathe are important for migraines. Smartphone migraine application (app) data provides more precise information about when migraine attacks start. This study will determine the association of local air pollution with migraine attack onset via both ER and smartphone data. The overarching goal of the interdisciplinary team is to validate the use of self-reported smartphone app data compared to administrative data in the context of environmental exposures and health outcomes.

Congratulations to the 2021-2022 Teams:

 

For additional details on the funded projects from 2021-2022, please see the DLSPH announcement. 

 

Using decision tree machine learning to identify worker movement typologies

PI: Aviroop Biswas (DLSPH)

Collaborators: Kathleen Dobson* (DLSPH), Stephanie Prince Ware (PHAC), Faraz Shahidi (Institute for Work & Health), Peter Smith (DLSPH)

Project description: Under the leadership of DLSPH Assistant Professor Aviroop Biswas, with co-investigators Kathleen Dobson (PhD Candidate, DLSPH), Stephanie Prince Ware (Research Scientist, Public Health Agency of Canada), Faraz Shahidi (Postdoctoral Fellow, Institute for Work and Health) and Peter Smith (Associate Professor, DLSPH), this project will explore the many and complex variables that affect working Canadians’ ability to engage in physical activity. Using the Canadian Health Measures Survey, the team will apply machine learning to over 11,000 respondents’ movement data, cardiometabolic markers, and socioeconomic and physical environment information.  The work will determine if an AI approach offers different findings from those obtained through traditional statistical methods, and aims to identify groups in the population that might most benefit from targeted interventions.

A multicentre database of patients hospitalized with diabetes in Ontario across 30 hospitals

PI: Michael Colacci* (IHPME/DLSPH), Michael Fralick (General Internal Medicine), Fahad Razak (General Internal Medicine)

Collaborators: Alanna Weisman (Mount Sinai), Amol Verma (General Internal Medicine), Bruce Perkins (UHN), Muhammad Mamdani (Unity Health Toronto), Chloe Pou-Prom (St. Michael’s Hospital), Patrick O’Brien (University Health Network), Esmerelda Carson (St. Michael’s Hospital)

Project description: DLSPH Master’s student Michael Colacci, together with clinician scientists Michael Fralick and Fahad Razak from University of Toronto’s Faculty of Medicine and eight co-investigators representing five different affiliate hospitals, will link data from the Ontario Diabetes Database and the General Medicine Inpatient Initiative platform (GEMINI database) to create a cohort of approximately 200,000 people who have been hospitalized with diabetes in Canada.  The new cohort will offer an incredibly rich source of data to evaluate the nature of inpatient care for diabetes – a disease affecting one in seven adults in this country.  The team will use the new database to evaluate which proportion of patients received the most up-to-date care, and apply an artificial intelligence-based prediction model to identify which groups of patients might be at highest risk of negative outcomes.

The evolution of potentially inappropriate prescribing in persons with dementia

PI: Abby Emdin* (DLSPH), Susan Bronskill, (DLSPH)

Collaborators: Peter Austin (DLSPH/IHPME), Colleen Maxwell (University of Waterloo – School of Pharmacy), Jennifer Watt, (Department of Medicine), Aaron Jones (ICES), Daniel Harris* (DLSPH), Jennifer Bethell, (DLSPH/IHPME)

Project description: DLSPH PhD student Abby Emdin and Professor Susan Bronskill (DLSPH, IHPME and ICES), together with six co-investigators with expertise across geriatric medicine, epidemiology and rehabilitation sciences are collaborating on a project that will apply network analysis to linked health administration data to understand prescription patterns for older adults newly diagnosed with dementia.  Using a study population of approximately 25,000 people in Ontario diagnosed between 2015 and 2019, the work will aim to identify the prevalence and circumstances related to patterns of over-medication.  The findings may be used to improve health system efficiency by detecting medication overuse, and also prevent inappropriate prescribing – and associated negative health outcomes – among people with dementia.  The use of network analysis methodology to patterns of drug prescribing is virtually unexplored, and this project will help identify the utility of this tool for future research in the field of pharmacoepidemiology.

Building Fair Machine Learning Models: Using Big Data to Explore Inequities in Risk Assessment at the Centre for Addiction and Mental Health

PI: Sean Hill (CAMH), Daniel Buchman (DLSPH)

Collaborators: Zoe Findlay* (CAMH), Katrina Hui (Department of Psychiatry), Marta Maslej (CAMH), Laura Sikstrom (CAMH), Juveria Zaheer (CAMH)

Project description: Sean Hill, Director of CAMH’s Krembil Center for Neuroinformatics, together with DLSPH Assistant Professor Daniel Buchman and five co-investigators with expertise across multiscale modeling, experimental and emergency psychology, translational science and bioethics, will evaluate whether biases might be built into the way risk assessment takes place in the context of psychiatric care.  Recognizing that both conventional risk assessment and different machine learning tools may be subject to bias, the team will use a mixed methods approach that combines an analysis of Electronic Health Records, participant observation, and interviews with clinicians and patients, to identify how ML tools might amplify existing inequities, such as racial bias, because they are trained on biased datasets.  Findings from the project will provide critical context and pilot data for future work using machine learning to redress these biases through fairer models.

ExplAIn 2 Kids: Engaging Children & Youth in Ar@ficial Intelligence in Pediatric Healthcare

PI: Melissa McCradden (DLSPH)

Collaborators: Dolly Menna-Dack (Holland Bloorview Kids Rehabilitation Hospital), Randi Zlotnik Shaul (SickKids), James Anderson (SickKids), Elizabeth Stephenson (SickKids)

Project description: In this project supported by the Edwin S.H. Leong Centre for Healthy Children, DLSPH Assistant Professor Melissa McCradden, together with co-investigators Dolly Menna-Dack (Holland Bloorview Kids Rehabilitation), Randi Zlotnik Shaul (SickKids), James Anderson (SickKids) and Elizabeth Stephenson (SickKids), will explore how children and youth understand and feel about the use of artificial intelligence in healthcare. The work aims to remedy the fact that there currently exist no explorations of the views of children and youth about the tools employed in their own care. The group brings expertise across qualitative health research, youth engagement, explainable AI, Bioethics, health law and research ethics. The project will generate new guidelines for clinical discussions with children about AI-assisted decision-making, create template language for informed consent forms for AI research studies, and launch a new agenda for healthcare AI engagement for children and youth.

Project funded by the Edwin S.H. Leong Centre for Healthy Children.

A Predictive Model for the Presence of Occult Cancer in Family Practice Patients

PI: Steven Narod (DLSPH)

Collaborators: Vasily Giannakeas* (DLSPH), Jennifer Brooks (DLSPH); Victoria Sopik* (Institute of Medical Science)  

Project description: DLSPH Professor Steven Narod, together with PhD candidates Vasily Giannakeas (DLSPH) and Victoria Sopik (Institute of Medical Sciences), and Assistant Professor Jennifer Brooks (DLSPH) aim to generate findings that might help develop a tool which can be used to predict the presence of cancer based on routine complete blood count tests that can be performed in any family doctor’s office.  In earlier work, this group linked data from the Ontario Laboratory Information System and the Ontario Cancer Registry to analyse the risk of cancer occurrences in over nine million adults in Ontario; they found that high platelet counts were associated with a more than five-fold risk of a solid cancer diagnosed within six months of the blood test.  In this new project, the team will evaluate more measures from original blood tests, incorporate additional variables such as age, sex and ethnicity, and apply statistical learning to improve the predictive values of their findings.  The goal will be to create a tool that researchers might subsequently evaluate in prospective studies.

*denotes project trainee