TORONTO, Nov. 27, 2025 鈥� 91亚色 welcomes 91亚色 Region鈥檚 decision to make a significant contribution of $25 million to support the new School of Medicine set to open to students in 2028.聽

The $25 million commitment will help fund the physical infrastructure and development of the School of Medicine, which will be built in the Vaughan Healthcare Centre Precinct, alongside the Cortellucci Vaughan Hospital. 

 鈥淥n behalf of 91亚色, I want to express my deepest gratitude to 91亚色 Regional Council members and Chairman Jolliffe for this extraordinary investment in the future of health care,鈥� said Rhonda Lenton president & vice-chancellor, 91亚色. 鈥淵our commitment of up to $25鈥憁illion for 91亚色鈥檚 new School of Medicine in the Vaughan Healthcare Centre Precinct will help us train the next generation of primary care physicians where they are needed most. This partnership reflects our shared vision to improve health outcomes, strengthen community well鈥慴eing, and build a resilient regional economy. Together, we are creating a model of integrated education and care that will serve 91亚色 Region and Ontario for generations to come.鈥�  

 This significant milestone represents ongoing positive momentum as the University ramps up work to engage local physicians, collaborate with health care and tech sector partners in the medical school鈥檚 future service area such as Mackenzie Health, Oak Valley Health, Southlake Health, and the (OCI).   

 鈥�91亚色 Region is proud to support this important investment in training future physicians right here in our own community. By contributing $25 million to 91亚色鈥檚 new School of Medicine, we are helping ensure that families across our communities have better access to the care they need, closer to home. This partnership reflects our shared commitment to strengthening the health and well-being of residents and building a future where everyone in 91亚色 Region can thrive,鈥� said Eric Jolliffe, 91亚色 Region Chairman and CEO.  

 91亚色 Region鈥檚 contribution builds on existing commitments from the Government of Ontario to fund the startup costs associated with establishing the medical school. The land for the new building has been generously donated by the City of Vaughan.    Together, these commitments strengthen momentum for the medical school, which is a much-needed part of the Ontario government鈥檚 expansion of medical education designed to address local physician shortages, enhance access to primary care, and support a long-term, sustainable health-care system.   

About the 91亚色 School of Medicine

The 91亚色 School of Medicine will be explicitly structured around a community-based primary care model, emphasizing inter-professional collaboration, equity, and patient-centred practice. Its location within the Vaughan Healthcare Centre Precinct 鈥� next to Cortellucci Vaughan Hospital 鈥� will facilitate strong connections between clinical training, research, and community health services.

About 91亚色

91亚色 is a modern, multi-campus, urban university located in Toronto, Ontario. Backed by a diverse group of students, faculty, staff, alumni and partners, we bring a uniquely global perspective to help solve societal challenges, drive positive change and prepare our students for success. 91亚色's fully bilingual Glendon Campus is home to Southern Ontario's Centre of Excellence for French Language and Bilingual Postsecondary Education. 91亚色鈥檚 campuses in Costa Rica and India offer students exceptional transnational learning opportunities and innovative programs, while at the Markham Campus, innovation, technology, entrepreneurship, and industry collaboration are built into every program. 91亚色鈥檚 new School of Medicine, the first Canadian medical school to focus on community-based primary health-care education, will welcome its first cohort in September 2028.

Media Contact: Yanni Dagonas, 91亚色 Media Relations, 647-468-7850 yannidag@yorku.ca

The post 91亚色 Region Council approves $25M to support 91亚色鈥檚 new School of Medicine appeared first on News@91亚色.

TORONTO, June 4, 2025 鈥� If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm. A new study out today from 91亚色 found proactive, continual and transfer learning strategies for AI models to be key in mitigating data shifts and subsequent harms.

To determine the effect of data shifts, the team built and evaluated an early warning system to predict the risk of in-hospital patient mortality and enhance the triaging of patients at seven large hospitals in the Greater Toronto Area.

The study used GEMINI, Canada鈥檚 largest hospital data sharing network, to assess the impact of data shifts and biases on clinical diagnoses, demographics, sex, age, hospital type, where patients were transferred from, such as an acute care institution or nursing home, and time of admittance. It included 143,049 patient encounters, such as lab results, transfusions, imaging reports and administrative features.

鈥淎s the use of AI in hospitals increases to predict anything from mortality and length of stay to sepsis and the occurrence of disease diagnoses, there is a greater need to ensure they work as predicted and don鈥檛 cause harm,鈥� says senior author 91亚色 Assistant Professor of 91亚色鈥檚 School of Health Policy and Management, Faculty of Health, a member of Connected Minds and a faculty affiliate at the聽Vector Institute.

鈥淏uilding reliable and robust machine learning models, however, has proven difficult as data changes over time creating system unreliability.鈥�

The data to train clinical AI models for hospitals and other health-care settings need to accurately reflect the variability of patients, diseases and medical practices, she adds. Without that, the model could develop irrelevant or harmful predictions, and even inaccurate diagnoses. Differences in patient subpopulations, staffing, resources, as well as unforeseen changes to policy or behaviour, differing health-care practices between hospitals or an unexpected pandemic, can also cause these potential data shifts.

鈥淲e found significant shifts in data between model training and real-life applications, including changes in demographics, hospital types, admission sources, and critical laboratory assays,鈥� says first author Vallijah Subasri, AI scientist at University Health Network. 鈥淲e also found harmful data shifts when models trained on community hospital patient visits were transferred to academic hospitals, but not the reverse.鈥�

To mitigate these potentially harmful data shifts, the researchers used a transfer learning strategies, which allowed the model to store knowledge gained from learning one domain and apply it to a different but related domain and continual learning strategies where the AI model is updated using a continual stream of data in a sequential manner in response to drift-triggered alarms.

Although machine learning models usually remain locked once approved for use, the researchers found models specific to hospital type which leverage transfer learning, performed better than models that use all available hospitals.

Using drift-triggered continual learning helped prevent harmful data shifts due to the COVID-19 pandemic and improved model performance over time.

Depending on the data it was trained on, the AI model could also have a propensity for certain biases leading to unfair or discriminatory outcomes for some patient groups. 

鈥淲e demonstrate how to detect these data shifts, assess whether they negatively impact AI model performance, and propose strategies to mitigate their effects. We show there is a practical pathway from promise to practice, bridging the gap between the potential of AI in health and the realities of deploying and sustaining it in real-world clinical environments,鈥� says Dolatabadi.

The study is a crucial step towards the deployment of clinical AI models as it provides strategies and workflows to ensure the safety and efficacy of these models in real-world settings.

鈥淭hese findings indicate that a proactive, label-agnostic monitoring pipeline incorporating transfer and continual learning can detect and mitigate harmful data shifts in Toronto鈥檚 general internal medicine population, ensuring robust and equitable clinical AI deployment,鈥� says Subasri.

The paper, , was published today in the journal JAMA Network Open.

The post New research finds specific learning strategies can enhance AI model effectiveness in hospitals appeared first on News@91亚色.

You鈥檝e just been given a prescription for a new drug from your doctor. Your doctor told you why she was prescribing the medication, gave you its name and some information about common side-effects. Your pharmacist is also available to help you use the medication properly, but you want more details and general information.

You鈥檇 also like to know things such as how quickly the drug was approved by Health Canada, whether there have been any recent safety warnings about the drug, how the drug compares to other medications for the same condition and what information Health Canada took into consideration when it approved the drug.

You鈥檙e aware that a general internet search may yield unreliable information, so you decide to look at what鈥檚 on the various Health Canada websites.

General information: The product monograph

Every drug that鈥檚 approved by Health Canada comes with what鈥檚 known as a product monograph (PM).  a PM 鈥渋s a factual, scientific document on the drug product that, devoid of promotional material, describes the properties, claims, indications, and conditions of use for the drug, and that contains any other information that may be required for optimal, safe, and effective use of the drug.鈥�

PMs can be downloaded from the  after you type in either the brand or generic name of the drug. Most of the document is written in language that would be hard for the average consumer to understand, but at the end there is typically a seven- or eight-page section of consumer information that offers more detailed information about issues such as safety, what the drug is used for and when you should avoid using it.

While the PM has to be approved by Health Canada, it is actually written by the company marketing the drug, and the actual contents are often subject to negotiation. It鈥檚 also not clear how often a PM is revised. All Health Canada says is that  when there is new safety information or when there are new uses of the drug, but there is no timeline given for how quickly those revisions need to be done.

Safety information

The PM will give you aggregate safety information, but it doesn鈥檛 tell you how many times doctors, consumers and manufacturers have reported safety concerns or if Health Canada has issued a safety warning.

For the reported safety concerns, you need to go to the .

For Health Canada鈥檚 health warnings, you鈥檒l need to go to the . However, when you get there, there are no instructions about how to do a search so it鈥檚 trial and error and hopefully you鈥檒l find what you need.

Information about clinical trials

Clinical trials are the studies that companies have to do before a drug can be marketed. But these studies usually only include a small subset of people who have the condition that the drug鈥檚 designed to treat. They often  groups such as the elderly, children, women who might become pregnant and people taking multiple other drugs.

If you want to know if the drug you have been prescribed has been tested on people similar to you, you can read section 7.1 of the  which gives details about the clinical trials. Information about the age and sex of patients in the trials is there, but unfortunately Health Canada only discloses that information in a .

How well does the drug work?

Will the drug make you feel better? Drugs are sometimes approved using what are called hard clinical endpoints, such as do you live longer and/or is your quality of life better. But drugs are also approved based on surrogate endpoints.

Surrogate endpoints are measures of things like changes in blood chemistry, blood pressure or how hard you can blow into a machine. These are supposed to predict what matters to patients 鈥� things like survival and quality of life 鈥� and sometimes they do as with drugs for HIV/AIDS that lower viral load, . But often surrogate endpoints don鈥檛. For example, only a minority of  on the basis that they shrunk the size of the tumour, a surrogate endpoint, actually helped people live longer.

The Summary Basis of Decision documents will tell you whether clinical or surrogate endpoints were used, and it turns out that  approved by Health Canada between 2012 and 2022 used surrogate endpoints. So, how much benefit you will get might be questionable.

How quickly was the drug approved?

You might want to learn about how long it took Health Canada to approve the drug. There are studies showing that the  once it is on the market.

Information about how fast a drug was approved used to be available by writing to publications@hc-sc.gc.ca for annual reports, and using the information in those reports to calculate review times. But in August 2022, an unannounced decision was made to cancel the annual reports. So, as of now, there is no information covering the period after March 31, 2022. It鈥檚 unclear if the annual reports will be resumed.

How does one drug compare to another?

You might notice that the drug you鈥檝e been prescribed for your problem is not the same one that your friend was prescribed for the identical problem. You may want to know which drug, on average, does a better job.

The  used to rank the additional therapeutic value of new drugs compared to existing ones on a scale from breakthrough to slight/no therapeutic value. Those rankings were done by an  and published each year in the PMPRB鈥檚 annual report. At least they were up until the long-delayed , which didn鈥檛 come out until February 2024. That report did not contain any rankings and the PMPRB has not said that publicly available information about rankings is going to come back.

Orphan drugs

If you have an  (one that affects fewer than one in 2,000 people) you often don鈥檛 have very many, or even any, treatment options. In those cases, you will want to know when new drugs are available that might help you.

Starting in 2018 Health Canada published an annual report that listed the new orphan drugs that it approved. But the ; since then, there have not been any new editions. So, now there is no new easily available information about new orphan drugs.

Finding out safety and effectiveness information about drugs shouldn鈥檛 be a hit and miss affair. Health Canada needs to do a much better job of providing all the information that concerned patients (and their caregivers) need in order to make sure that patients get the best possible results from the drugs that they use.

By 91亚色 Professor Emeritus Joel Lexchin, Faculty of Health.

This article is republished from .

The post How to find more information about a drug that your doctor prescribed appeared first on News@91亚色.