Health at Vector
Canadians have an unprecedented opportunity to harness world-leading AI research and innovation to build on the data advantage stemming from our public health system.
Vector supports and enables its partners in the health and academic sectors to implement leading edge AI research to support better whole-life health.
Health is a key pillar in Vector’s Three-Year Strategy
Towards better whole-life health, Vector will enable effective & appropriate research access to health data.
We believe all Canadians deserve to benefit from modern health care solutions using the best technologies and tools available. We are uniquely positioned to convene and facilitate partnerships among scientists, government, and public health institutions to help health practitioners and policy-makers use the best-available AI tools to improve patient outcomes and health care delivery. Key to applying AI and working with de-identified Ontario health data is the development of a modern health data governance framework that both protects privacy and encourages the adoption of innovative life-saving technologies. With a practical and enforceable framework in place, we will be able to take advantage of industry’s ability to develop and scale innovative technologies for modern health care and to contribute to health-related insights.
Excellence in Health-AI Research
Co-hiring with health
Vector works with health care organizations to recruit top AI talent to the sector, enabling access to collaborations with Vector’s AI community and compute power. If you are interested in partnering with us to support co-recruitment of global talent engaged in health AI research, get in touch.
Meet our health-AI researchers
Many members of Vector’s community are working on health-AI research.
Responsible Health Data Access for Research
Realizing the potential of AI to improve patient care and reduce health service delivery costs begins with access to high-quality data. Vector has made significant strides in facilitating improved access to health data, and in defining modern health data governance frameworks to provide researchers with secure access while protecting patient privacy. To further advance responsible data access, Vector is working with partners and collaborators in the health data ecosystem to align efforts.
Modern health data governance framework
Together with health stakeholders, Vector is leading the development of a modern health data governance framework to ensure that research conducted on Vector’s AI-optimized hardware is secure and that privacy is protected.
General Medicine Inpatient Initiative (GEMINI)
Vector is working with the GEMINI Team, based at St. Michael’s Hospital, Unity Health Toronto, to understand and improve the quality of hospital care drawing on one of the largest sets of hospital inpatient data in Canada.
T-CAIREM
Vector is collaborating with the University of Toronto’s recently launched Temerty Centre for AI Research and Education in Medicine (T-CAIREM) to advance areas of aligned priority, including data governance and infrastructure. T-CAIREM seeks to establish world-class educational programs in AI in medicine, fund research opportunities that bring together experts from a range of disciplines, and create a secure data platform to house datasets for applied AI learning and research.
Health AI Data Analysis Platform (HAIDAP)
We partnered with the Institute for Clinical Evaluative Sciences (ICES) and HPC4Health at the Hospital for Sick Children and the University Health Network to construct and update the Health AI Data Analysis Platform (HAIDAP) — a secure computing environment that allows researchers to use machine learning tools and methods to analyze de-identified population-level health data to generate more accurate health insights and predictions.
Data Partnerships
Organizations across Canada hold large volumes of data that can be used to generate important health insights and develop novel solutions using machine learning.
Vector may be able to help connect your organization to the right tools and talent to harness this strategic advantage, develop strong data-driven collaborations and enable you to learn more about secure and appropriate computing environments.
Working with Industry
Industry plays a vital role in developing and bringing to market innovative and sometimes life-saving health care solutions. Service providers like insurers, banks, and retailers capture behavioural and sociodemographic data that could deepen health care providers’ understanding of factors that affect Ontarians’ health.
Through its industry sponsorship program, Vector works with companies across all sectors to enhance their AI capabilities and develop innovative business solutions and insights. Industry sponsors get access to a suite of Industry Innovation programs designed to accelerate the application of advanced AI in their organizations. These programs bring together Vector’s world-renowned researchers, advanced compute environment, diverse talent community, and AI engineering capabilities to support organizations working to transform AI into business value.
AI Deployment in Health
Vector is committed to convening and facilitating partnerships among scientists, government, and public health institutions to help health practitioners and policymakers use the best-available AI tools to improve patient outcomes and health care delivery.
Vector is helping to deploy AI technology in the health sector, facilitated by initiatives such as Vector’s Smart Health initiative, which allow for the scaling and deployment of machine learning tools in hospitals across Ontario.
Pathfinder Projects
The Vector Institute has supported a series of Pathfinder Projects to implement AI-assisted technologies in the health sector. Pathfinder Projects are small-scale efforts designed to produce results in 12 to 18 months that guide future research and technology adoption.
Health AI Deployment Symposium
With Anna Goldenberg’s leadership and in partnership with The Hospital for Sick Children (SickKids), Vector organized a Health AI Deployment Symposium to showcase examples of AI research translated into practice in health care. Insights were published in a white paper.
AI Training for Health Practitioners
The Vector Institute is partnering with the Michener Institute of Education at UHN to design educational and training curriculum focussed on front-line healthcare professionals in the effective, appropriate, safe, and compassionate use of AI within their scope of practice. In order to put the needs of patients first in creating a healthier community using AI, the project will also involve patients in the design and development of programs.
In the News
- Vector Institute Introduces A Smart Health Initiative To Drive Innovation In Healthcare: Smart Health will enable collaboration between researchers and hospitals towards better care and health outcomes with greater system efficiency
- Essential Requirements for Establishing and Operating Data Trusts: practical guidance from a working meeting of Canadian organizations and initiatives
- Implementing AI in healthcare: an overview of the Health AI Deployment Symposium which took place in Toronto, Ontario on October 30th, 2019 as a joint collaboration between the Hospital for Sick Children and the Vector Institute
- CTV Kitchener: AI system more accurately identifies collapsed lungs using chest x-rays
- CityTV: Artificial Intelligence to give Toronto doctors a 2nd opinion
- Canadian Healthcare Technology: Artificial intelligence makes strides as an intelligent assistant
- Globe and Mail: SickKids announces Vector Faculty Member, Anna Goldenberg, as the hospital’s first chair in biomedical informatics and artificial intelligence
Recent published research
- BIONIC: Biological Network Integration using Convolutions: Bo Wang
- One Cell At a Time: A Unified Framework to Integrate and Analyze Single-cell RNA-seq Data: Bo Wang, and other contributors
- Deep learning classification of unipolar electrograms in human atrial fibrillation: Application in focal: Bo Wang, and other contributors
- Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality: Bo Wang, and other contributors
- Genetic mechanisms of critical illness in Covid-19: Bo Wang, and other contributors
- Machine Learning Compared To Conventional Statistical Models For Predicting Myocardial Infarction Readmission And Mortality: A Systematic Review: Bo Wang, and other contributors
- Long-term mortality risk stratification of liver transplant recipients: real-time application of deep learning algorithms on longitudinal data: Bo Wang, and other contributors
- A MACHINE LEARNING MODEL FOR CHARACTERIZATION OF MIXED AORTIC VALVE DISEASE PATIENTS: Bo Wang and other contributors
- Predictors of Mortality Among Long‐Term Care Residents with SARS‐CoV‐2 Infection: Bo Wang, and other contributors
- The cardiac surgeon’s guide to artificial intelligence: Bo Wang, and other contributors
- Machine Learning as a New Frontier in Mitral Valve Surgical Strategy: Bo Wang and other contributors
- simATAC: a single-cell ATAC-seq simulation framework: Bo Wang and other contributors
- Pathogenic Germline Variants in Cancer Susceptibility Genes in Children and Young Adults With Rhabdomyosarcoma: Anna Goldenberg and other contributors
- Dear Watch, Should I Get a COVID-19 Test? Designing deployable machine learning for wearables: Anna Goldenberg and other contributors
- Towards Robust Classification Model by Counterfactual and Invariant Data Generation: Anna Goldenberg and other contributors
- Considerations for Visualizing Uncertainty in Clinical Machine Learning Models: Anna Goldenber and other contributors
- Integration of brain and behavior measures for identification of data-driven groups cutting across children with ASD, ADHD, or OCD: Anna Goldenberg and other contributors
- Single-cell mapper (scMappR): using scRNA-seq to infer the cell-type specificities of differentially expressed genes: Anna Goldenberg and other contributors
- Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings: Anna Goldenberg and other contributors
- 3D Reasoning for Unsupervised Anomaly Detection in Pediatric WbMRI: Anna Goldenberg and other contributors
- Identifying Modifiable Predictors of Long‐Term Survival in Liver Transplant Recipients With Diabetes Mellitus Using Machine Learning: Anna Goldenberg and other contributors
- A comprehensive EHR timeseries pre-training benchmark: Anna Goldenberg and other contributors
- Unsupervised representation learning for time series with temporal neighborhood coding: Anna Goldenberg and other contributors
- Identification of Optical Coherence Tomography Phenotypes and Their Relationship with Patient Outcomes in Youth With Demyelinating Syndromes: Preliminary Results of an …: Anna Goldenberg and other contributors
- NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning: Anna Goldenberg and other contributors
- Predicting Malignancy with Pediatric Thyroid Nodules: Early Experience in Machine Learning for Clinical Decision Support: Anna Goldenberg and other contributors
- Standardized Reporting of Machine Learning Applications in Urology: The STREAM-URO Framework: Anna Goldenberg and other contributors
- How interpretable and trustworthy are gams?: Anna Goldenberg and other contributors
- MP44-18 ACCURATE ESTIMATE OF SPLIT DIFFERENTIAL RENAL FUNCTION USING ULTRASOUND ALONE FOR INFANTS WITH HYDRONEPHROSIS: Anna Goldenberg and other contributors
- Finding associations in a heterogeneous setting: Statistical test for aberration enrichment: Anna Goldenberg and other contributors