This is largely the current situation when it comes to artificial intelligence (AI) applications in space. Space missions are complex endeavours that involve travelling great distances, harsh environments and many unknown factors, and they cost hundreds of millions to billions of dollars from conception to completion. While there is an inherent level of risk that is undertaken to do the work, a certain level of conservatism is also necessary to ensure a mission’s success.

“AI works in a non-linear way. This is the advantage of AI, what makes it so powerful.”

While some labs at �첥��Ƶ are creating technologies that are applied to actual space missions today, the work being done to develop AI applications is looking towards a future, exact date unknown, where AI robots will take over much of the labour of space exploration. In some cases, that technology is simultaneously being translated to applications on Earth, where there are far less environmental constraints, but the need for greater trust in AI is no less important, say the researchers at York’s Lassonde School of Engineering who are developing next-generation technologies.

Decades ago, ’s interest in space robotics was piqued after NASA launched the Hubble telescope, only to announce shortly after that the mirrors Hubble relied on to capture images of distant galaxies were flawed and all the images it captured were blurry. NASA looked into the feasibility of sending robots to fix the issue, but later abandoned this approach, instead sending astronauts. Yet, the idea of using space robots to service and fuel crafts intrigued Zhu and it remains an area of research interest to the present day. Now a professor at York and director of the Space Engineering Design Laboratory, he is developing robotics and AI future applications for MDA Space – Canada.

“AI works in a non-linear way. This is the advantage of AI, what makes it so powerful. But because of its unexplainable nature, because you cannot disentangle it, the space industry does not currently trust it, but is still very much interested in exploring the future of these powerful potentials,” he says.

Currently, explains Zhu, every time a satellite or craft is launched into space, an exact replica is created and left on Earth, so if something goes wrong, engineers can work with the replica to pinpoint the error and fix it. AI, in not showing its work, does not lend itself to such easy corrections.

While colleagues at MDA are attempting to create explainable AI to address this concern, Zhu is working on other pieces of the puzzle, often not involving the most powerful and complex AI technologies, but simpler ones that might be able to be adapted to space sooner. These include simulations to train AI vision for the low-level light conditions that exist in space when approaching a spacecraft; robotics and AI swarming technologies that involve several AI robots that are not the most powerful, but can work together to do more complicated tasks; and training AI robots on learning tasks like grip strength. Zhu is also looking at developing lightweight materials that can be used in space as radiation shields, as the sophisticated AI chips developed by companies like Nvidia cannot currently be used in space.

Associate Professor , director of the Astronautics and Robotics Laboratory at York, says that while his field used to be focused on fairly traditional methods, that is beginning to change. “Previously, this work has been dominated by classical techniques, but I would say in the last 10 years or so, we’ve seen a huge expansion where there’s interest in how we can apply machine learning, reinforcement learning, deep learning, deep reinforcement learning and computer vision to these fields.”

While space does pose unique challenges in terms of the environment, Bazzocchi says that many of the technologies they develop for space can be applied to the benefit of humans on earth and vice versa.

“While they’re not the same problem, they have many similarities that allow us to apply related techniques.”

One example from his work is an exoskeletal suit designed for firefighters to reduce the amount of effort required while doing strenuous tasks. Part of this lab work requires motion capture to understand a firefighter’s movements, but also requires employing different optimizations and algorithms to understand how the device might reduce or increase muscle activation in ways that might be beneficial.

"If you could send out autonomous robots first, they could perhaps create the right conditions for the humans to follow.” 

In space, the challenge for astronauts is quite the opposite: zero gravity conditions lead to muscle atrophy and eventually bone loss. The same research and principles can create wearables that purposefully create more resistance for astronauts when executing basic tasks.

“It’s not artificial gravity, because it won’t bring them to the floor, but it will make their movements more difficult,” he says. “When they want to do a task, for example, and they have to flex their arm, there’s a motor that’s resisting the motion so that it is not as easy.”

While the possibilities are exciting, Bazzocchi says that in both scenarios, machine learning and AI are not yet trusted.

“When you’re dealing with humans, you want predictability, and very obvious control that’s not going to potentially do something that’s unexpected and lead to injury,” he says. “And the same thing goes for space, when dealing with these multi-million-dollar assets, you want a certain level of predictability and explainability if something goes wrong.”

Still, Bazzocchi thinks it won’t be long until AI plays a bigger role in space.

“There have been some applications of autonomy in space already, such as for time-sensitive operations where there are long time-delays or for doing data processing. So, for example, creating algorithms that evaluate Earth imagery to detect wildfires is very much already in play.”

Zhu says that one day AI technologies might develop to the point where they can pave the way for creating hospitable living conditions for humans in space.

“Elon Musk wants to send humans to Mars. I think in the short term, it’s very difficult because the astronauts would die, the radiation exposure would be too much. But if you could send out autonomous robots first, they could perhaps create the right conditions for the humans to follow,” says Zhu.

Still, how would we know that the robots, working together and autonomously settling Mars, would still act in the interest of the humans that sent them there?

That’s the billion-dollar space robotics question, and according to the researchers, one we don’t currently have an answer for.

The post Space robotics appeared first on Ascend Magazine.

At �첥��Ƶ, a team of researchers is currently collaborating to develop robots to protect and make life better for the elderly, with the potential for game-changing applications across the spectrum of elder care.

“The possibilities are endless,” says , a professor at the University’s Lassonde School of Engineering and Faculty of Health, who is co-leading CINTHeA: Co-creating Intelligent Neuro-Technologies for Healthy Aging, together with Professor Vincent DePaul from Queen’s University.

“Social robotics for older adult care has been explored for many years. But to date, most of the traction has been achieved with comfort robots – furry pets that people can hold and care for – and that’s great, but we know we can go further.”

Japanese companies were early out of the gate with life-like robotic pets to provide companionship to a massive aging generation. Paro, a therapeutic robot, with all the cuddliness of a baby seal, responds to touch, sound and eye contact in a way that can comfort elderly patients in hospitals. The more penguin-like LOVOT (short for love robot) coos when hugged, creating a bond with its human owner and, as it demands affection, a sense of purpose.

CINTHeA aims to get the technology to the next level, where robots move autonomously around places where people live and can provide social, cognitive and physical assessment and assistance.

Elder says that when integrated with recent advances in artificial intelligence (AI), robots can contribute in many ways, helping to socially engage isolated seniors, and assess pain, emotional state and cognitive health. They may also help assess gait, posture and risk of a fall. Together, these contributions can help extend the health span of older adults and help health-care workers in assisted living and long-term care facilities.

“What we’ll see in the next 10 years is an expansion to more general capabilities for robots that will really make a difference to both older adults and staff,” he says.

“The possibilities are endless.” 

The project has set its sights high. Its mission is to reshape the future of aging with dignity, autonomy and inclusion by creating new AI and robotics technologies to help assess, assist and engage older adults and improve their quality of life. Success will rely on a wide diversity of expertise. Neuroscientists are working with engineers, social scientists and experts in elder care, and the project is also relying on the experiences of older adults, their families and caregivers.

It is publicly funded with a $1.5-million Canada First Research Excellence Fund grant through the massive, �첥��Ƶ-led Connected Minds program that seeks to understand the opportunities and risks to society associated with advancing technology. It is also tied to a $3-million infrastructure application proposal made to the Canada Foundation for Innovation.

Partners who specialize in geriatric residential living, research and innovation, such as Baycrest Health Sciences, the Unionville Home Society, Seasons Retirement Communities and Oasis Aging Well, as well as technology companies like CrossWing, GlobalDWS and Esri Canada will help translate the research into practical solutions.

Mobility has long been recognized as a cornerstone of healthy aging. Without it, people can become isolated from social and physical activities, and unable to access resources in the community.

As part of CINTHeA, Distinguished Research Professor Shayna Rosenbaum, York Research Chair in Cognitive Neuroscience of Memory in York’s Faculty of Health and associate director of the Centre for Integrative and Applied Neuroscience, is focused on how mobility robotics can help older adults move around.

“We can train the robot to navigate and to make errors the way a human would, so that the robot would be better able to reorient a person who appears lost,” says Rosenbaum, vice-director of Connected Minds. She is researching what strategies older adults use in real-life situations to compensate when neurological conditions affect how they get around. The findings will play a role in how assistive robots are programmed to assess how elderly people navigate when they move into new health-care environments and make it easier to adapt, for example.

Rosenbaum has been interested in navigation and how it changes in aging adults since watching her four grandparents grow older – all immigrants to Canada, having to navigate new environments without drivers’ licenses. “None of my grandparents drove,” she says. “That was very striking to me. Their world was relatively small, at least when it came to space. It piqued my interest in how this type of diminished experience might affect brain function.”

“It became a critical question, ‘how can we deliver better later life care?’”

Elder, who is also York Research Chair in Human and Computer Vision, comes at it from a different perspective. His research has been focused on understanding human perception and building machine vision systems that are inspired by that understanding. “The framework is to try to build AI systems that are more human, and able to do human-like things. So, progressing from factory floor kind of automation to systems that can work in less controlled and more complex environments.”

Elder and Rosenbaum watched the pandemic’s devastating effect on older Canadians, especially those living in institutions, and want to leverage the spotlight COVID provided to do better.

“It became a critical question, ‘how can we deliver better later life care?’ And this seems like this is really a huge opportunity,” Elder says. “Not to replace human care, but to try to help these frontline staff who are really doing the angels’ work.”

Like anyone watching the increasing reliance on AI and its uncertain future, both Elder and Rosenbaum have an eye on the associated risks.

“These technologies can be incredibly useful in helping people lead independent lives longer, but at the same time, they might introduce levels of risk to privacy and security that we might not even anticipate. We have to look at how to mitigate risk while enhancing the benefits,” says Rosenbaum.

Another concern is that overuse of robotics can diminish the person’s ability to maintain flexible thinking.

“Eventually, it might lead to further decline,” she says. “We have to try to assess risk in ways that allow us to move forward, but do so cautiously.”

Elder agrees that there has to be a balance. “The goal is to maintain maximal human agency and only provide assistance when it’s required.”

The post The future of aging appeared first on Ascend Magazine.

The research team, led by Assistant Professor of York’s Lassonde School of Engineering and Laboratory of Advanced Biotechnologies for Health Assessment (LAB-HA), is developing a wearable biosensing device that promises to revolutionize preventative health care.

The non-invasive wearable device integrates microfluidic technology and advanced sensors to offer real-time insights into various physiological states by analyzing sweat.

The project, Revolutionizing Preventive Healthcare: A Wearable Device for Continuous, Non-Invasive Health Monitoring, is backed with $150,000 in funding from the Ontario Centre of Innovation (OCI) Collaborate 2 Commercialize program, with an additional $150,000 provided by project contributor SynHiTech Inc., a biotech incubator. Through WearNovAi, Salahandish and team are aiming to take the technology from the lab to the market in the next couple of years.

Over the next two years, researchers will work to develop, test and bring this cutting-edge technology to market, offering the potential for early disease detection and timely intervention.

“Traditional medical assessments often require invasive procedures like blood draws and laboratory analysis, where our wearable biosensing device will offer a convenient, userfriendly alternative for ongoing health monitoring,” says Salahandish.

“This innovative approach to preventative health care empowers individuals to take charge of their health and has potential for wide adoption across the health-care sector.”

By continuously collecting and analyzing sweat samples, the device can detect subtle physiological changes associated with disease progression, providing early indications of potential health issues before symptoms appear, she explains.

“This makes it a valuable tool for individuals at higher risk of developing chronic conditions or those who wish to proactively monitor their health,” she says.

One of the distinct features of this device is its use of advanced artificial intelligence algorithms to recognize specific patterns in the collected data providing actionable insights tailored to each user. This personalized approach could offer individuals the opportunity to monitor their own health alongside their health-care providers.

 Salahandish says the device combines comfort, accessibility and precision, making it an ideal choice for continuous health monitoring.

“This innovative approach to preventative health care empowers individuals to take charge of their health and has potential for wide adoption across the health-care sector,” she says.  

The post Sweat equity appeared first on Ascend Magazine.

“What excites me most about mechatronics engineering is the creativity, empathy and big-picture thinking it demands,” she says.

“We’re preparing students to lead in a world transformed by AI – equipping them to use it as a tool, understand its limitations, and apply it ethically and responsibly to solve problems people care about most.”

This integrated and interdisciplinary degree will give students the broad, higher-level engineering skills necessary to use advances in artificial intelligence (AI) and other technologies to solve today’s complex challenges.

As we increasingly rely on more advanced, often AI-driven technologies, future graduates of the program could be the ones to create next-generation medical devices to improve patient care, design renewable energy systems or develop smart technologies that can be integrated into people’s homes, workplaces, schools and communities to improve lives.

“I would absolutely recommend the mechatronics program to students who are looking for a balance of creativity, design and technology.”

What makes the program stand out is that students take courses in mechanical, electrical, software, computer and space engineering, as well as computer science, which gives them the tools to be more creative and innovative. Hands-on learning is a large component of their studies and could include working on systems for spacecraft attitude control, drone navigation and robotic automation, as well as vibration testing, satellite communications, flight software development and hardware testing for components heading into space.

“The goal of mechatronics is to provide the necessary technical background so that any graduate is well-prepared for that, but also providing the soft skills, work and life experiences that will make them well-suited for careers in industry,” says Mechatronics Program Director Michael Jenkin, also a professor at Lassonde. “One of the things that’s particularly exciting about mechatronics is that the systems interact with the real world. So, it’s not just something in software that exists in simulated isolation.”

In the first-year block model option, students focus on one course at a time rather than juggling several at once. Lassonde has tested this approach in recent years, and early results show it is helping students achieve higher grades, reduce stress and find a better study-life balance. Another innovation is cross-year collaboration, with students in upper years acting as mentors to students in lower years.

Third-year engineering student Chantal Hanna, who recently transitioned into the mechatronics engineering discipline to prepare for a career in robotic automation, says the program opens doors to a wide range of emerging fields.

“I would absolutely recommend the mechatronics program to students who are looking for a balance of creativity, design and technology,” says Hanna.

“Mechatronics is teaching me to see technology not just as machinery, but as a way to connect with the future and innovate with purpose. There are always new advancements in tech, and this is the field that will continue to grow alongside those advancements.”

Students will also gain work experience through two mandatory work terms, plus optional co-op placements. “With work-integrated learning and strong employer partnerships, our graduates will be ready to shape technology that connects with society and ensures AI serves people first,” says Goodyer.

The post Technology to the students appeared first on Ascend Magazine.

It felt like a near miss. Had I been on a later flight, I would have been caught up in the aftermath of airport operations disruptions and passenger confusion with hundreds of cancellations and delays over several days.

�첥��Ƶ experts in disaster and emergency management, artificial intelligence (AI) and software engineering say these kinds of crises require highly complicated and detailed responses involving multiple people and systems, from first responders and airport operations to government agencies, working seamlessly together. In a world where AI is bursting into the mainstream, two �첥��Ƶ professors believe the effect of AI on airports to help better choreograph the many pieces during a crisis could have a huge impact.

Research and Training on the Future of Airports is the newest project of y, director of CIFAL York and executive director of at York, and , associate director of CIFAL York. As part of the project, they will research and develop AI solutions for airports to help minimize risk and better coordinate response and recovery operations to ensure timely medical intervention, evacuation and safety in a crisis.

“During a disruption, there is the potential for AI to allocate staff, reroute baggage flows, or simulate different recovery scenarios to help airports respond and recover quickly and in a coordinated way,” says Nayebi.

The project positions CIFAL York as a global leader in how airports prepare for these challenges together with the United Nations Institute for Training and Research’s Airports and Economic Development Global Training Programme, with AI as an important piece.

“AI can help minimize the risks, help airports prepare for emergencies, respond better to emergencies, and recover or continue their operations after the emergencies."

The professors believe AI can have a much deeper role in operations. “There are possibilities for predicting potential hazards, impacts on airport operations using AI analytics, for example, considering external factors like weather conditions,” says Asgary. He is part of York’s undergraduate and graduate in the Faculty of Liberal Arts & Professional Studies and Faculty of Graduate Studies – the only graduate program of its kind in Ontario and one of only two in Canada.

“AI can help minimize the risks, help airports prepare for emergencies, respond better to emergencies, and recover or continue their operations after the emergencies. In our view, because airports have robust data collection for many of their functions, they are ideal when it comes to implementing AI analytics to help with solutions.”

Although last winter the emergency was a plane crash, it could have been a hurricane, flood, earthquake, tornado or fire. A crisis could also include a strike by airline workers or a cyber attack. These types of internal, external and regional crises can affect airport operations as well as the larger community. The capabilities of AI in airport operations goes far beyond that of a chatbot for communicating with passengers or fixing baggage snags.

“The research teams have demonstrated that the true pain points lie deeper in the coordination of systems and actors that make an airport run. A digital interface may reassure passengers, but without integrated operations behind it, the experience remains broken. The research is instead focusing on AI for coordination of systems to connect airlines, ground handlers, security and local authorities to act faster and smarter together,” says Nayebi of York’s Lassonde School of Engineering.

“Airports today are more than transit hubs, they are miniature cities with complex infrastructures, vast workforces, massive temporary users and immense economic influence. They are critical infrastructures that must continue to function in the face of pandemics, extreme weather, system disruptions and large-scale events such as the FIFA World Cup.”

AI can be used to predict and mitigate weather disruptions to flights and help coordinate the movement of planes and people inside and outside, as well as identify how resources will be impacted and what will be needed.

Using internal data as well as external emergency preparedness data, AI models and simulations can help anticipate and alleviate the impact on airports and passengers when incidents happen by ensuring airports can respond better during a crisis. This could mean evacuating the airport, deploying fire, police and other emergency crews, crowd management or acting as a hub for aid distribution.

“Using tools such as cameras with AI-based computer vision, airports can now detect a lot of potential hazards on the runway, such as birds, cracks, snow and animals, to prevent a crash. These tools, for example, can detect or identify a wrong person coming into the terminal or understand how passengers will react to a particular incident, like a fire,” says Asgary. “In risk and emergency response, there’s a whole lot AI can do.”

GenAI tools can be used to inform passengers during normal operations, but also in emergencies. With airports being a multicultural and multi-language hub, that information could be translated into each passenger’s first language and sent to their cell phone. “You can’t expect people to respond or react if the emergency is only broadcast in one language,” says Asgary.

“The goal,” says Nayebi, “is to equip airports over the next two to three years with AI-enabled resilience strategies to improve reliability, coordination and ultimately public trust in these vital infrastructures.”

These could include evidence-based guidance for governments and airport authorities, AI systems that anticipate disruptions and optimize airport-wide responses, tools that use data and simulation to support crisis decision-making, and training programs to help decision-makers adopt these tools responsibly and effectively.

Safer, smarter, more resilient airports are possible, says Nayebi. “For governments, the message is clear: supporting innovation in airports is not just about better travel, it is about building national resilience, economic opportunity and public trust.”

CROWD CONTROL

Countless people have died the world over in crowd crush incidents, whether at political rallies, sporting events or concerts, including in Canada, Germany, India, the United States and Ghana.

Concert goers this summer at the Rogers Stadium in Toronto got first-hand experience in the messiness and potential danger of crowds, with some commenting after the first couple of events about the need for better planning, particularly as people were leaving the busy venue. As Toronto and Vancouver prepare to host several FIFA World Cup matches in 2026, averting disaster through proper crowd management is top of mind for Asgary and Nayebi, whose work also includes crowd disaster mapping and simulation.

“Crowd management at large gatherings has become a major focus at various levels,” says Asgary. “While large sports events are common in major Canadian cities, the crowd typical of the World Cup is unfamiliar to crowd managers in Canada.”

“Crowd management is no longer just about counting people; it’s about understanding patterns, predicting risks and adapting in real time."

Nayebi and Asgary say that new and emerging technologies can not only help prepare for crowd management in advance but also provide support during events. They are now integrating these tools with AI and drone technologies to enhance crowd emergency management.

“We tested some of these integration efforts in summer 2025 during the Canada Day event in Vaughan, where our AI and drone-based crowd monitoring team was embedded within the Emergency Management team,” says Asgary. “Our ability to dynamically count and measure crowd behaviour in time and space is a crucial part of crowd management. Using a combination of drone, AI, virtual reality, digital twin and simulation tools, crowd management can be significantly improved.”

With these new technologies, a virtual representation of a concert or sporting event can be created, allowing for a more in-depth view of how to improve crowd management at specific venues.

“Crowd management is no longer just about counting people; it’s about understanding patterns, predicting risks and adapting in real time. By integrating machine learning and simulation with affordable technologies like drones and digital twins, we can design software-driven systems that help prevent tragedies before they unfold,” says Nayebi.

With a recent Global Research Excellence Seed Fund grant from York International, Asgary and Nayebi will also focus on helping multiple African countries by using more affordable technologies like drones and AI for crowd monitoring. In collaboration with Kwame Nkrumah University of Science and Technology in Ghana and the Africa Council of the International Association of Emergency Managers, the team hopes to develop a lasting partnership focused on research, training and knowledge exchange to reduce the occurrence and impact of crowd disasters.

The post The sky is the limit appeared first on Ascend Magazine.

AI can analyze huge, data-rich medical images and enormous quantities of data much faster than a human, but also sometimes better, observing the tiniest of details or changes that doctors cannot see, but that could necessitate a different course of patient treatment. These AI tools can also provide outstandingly accurate predictive analyses.

When it comes to cancer and liver transplant patients, it could mean the difference between a poor outcome and a higher survival rate. �첥��Ƶ researchers of the Lassonde School of Engineering and Divya Sharma of the Faculty of Science are developing AI tools for specific tasks that in some cases give clinicians information they otherwise would not have, with real-world implications for patients.

An associate professor, Sadeghi-Naini is developing AI tools coupled with imaging for brain, ovarian and breast cancers to characterize, monitor and predict different biological processes.

“We can scan these patients ahead of time using state-of-the-art ultrasound..."

He is the principal investigator of a new research project in collaboration with Women’s College Hospital with funding from the New Frontiers in Research Fund to develop a cost-effective, accessible AI platform to analyze the digital pathology images of ovarian cancer. The goal is to determine whether the patient has a genetic condition called homologous recombination deficiency without performing expensive genomic testing.

“It is an important factor in determining if the patient can benefit from available targeted therapies or not, but currently it requires genomic instability analysis to find out that is costly and not always accessible,” says Sadeghi-Naini, director of the Quantitative Imaging and Biomarkers Laboratory at York. That project is just beginning.

“I am also leading projects in collaboration with Sunnybrook Health Sciences Centre to develop AI frameworks that analyze digital pathology images of routine biopsy samples to predict treatment outcomes for individual breast cancer patients before they go through chemotherapy, to predict their response to treatment. It shows very promising results.”

Innovation York and Sunnybrook, where Sadeghi-Naini is a cross-appointed scientist, are currently in partnership to commercialize a couple of those tools for use.

In about 30 per cent of cases, chemotherapy does not work to shrink tumours effectively, as is the case with some high-risk breast cancers, but currently this is often determined months later after the completion of chemotherapy. “We can scan these patients ahead of time using state-of-the-art ultrasound to acquire raw signal data that after signal processing will generate quantitative ultrasound parametric images.”

The tool can then analyze those images deeper, faster and in more detail, as well as predict patient response to chemo before or shortly after it starts. It is important information that would allow oncologists to choose different treatment options if a chemo regimen is predicted not to work, which could significantly alter the survival rate of those patients who do not respond well.

“Studies show that the response of patients to upfront chemotherapy is linked to survival. Good responders show significantly better survival compared to poor responders,” says Sadeghi-Naini.

He is also working on an AI solution to a different problem, this time for brain cancer patients.

Following stereotactic radiotherapy for brain tumours, there is an up to 25 per cent chance a patient will experience radiation necrosis, a complication that can occur months to years later and is difficult for doctors to discern from brain tumour recurrence or progression.

“The problem here is that on the standard anatomical imaging, they appear very similar to each other,” he says. “That’s a challenge because radiation necrosis and tumour progression are two quite different things with different treatment approaches.”

In a recent study involving more than 90 patients with 230 brain tumours, Sadeghi-Naini and the team developed an AI platform that can analyze images of the brain using a new advanced MRI technique. Manually analyzing tumours on this multi-channel MRI is complicated, but with AI-guided methods it is much easier to distinguish between radiation necrosis, tumour progression or tumour recurrence.

“Our AI tools will not only help to predict but also improve long-term health outcomes for transplant patients by reducing disparities.”

He also leads development of an AI system to streamline analysis of repeated MRI scans for each brain cancer patient, a faster process that can better monitor and categorize tumour changes from one scan to another. In addition, he is working on an AI platform that can analyze early imaging of brain tumours and detect features invisible to the human eye, but that can provide information on the long-term outcome of the tumour, which may require a change in treatment.

“These are all cost-effective AI decision support tools for oncologists that inform personalized treatments and streamline their daily workflow, ultimately contributing to better patient care,” says Sadeghi-Naini. His research has garnered funding from the Natural Sciences and Engineering Research Council of Canada (NSERC), the Canadian Institutes of Health Research (CIHR), the National Research Council of Canada, the Terry Fox Foundation and others.

Sadeghi-Naini does not think AI can replace oncologists or radiologists, but says, “it can provide valuable complementary information, improve accessibility to precision therapeutics, save time and resources, and streamline and triage more complicated cases for expert review,” all providing added benefits to patients.

Sharma, an assistant professor and co-principal investigator on two recent CIHR project grants worth close to $3 million, is creating more equitable access to liver transplants through a national framework and developing a multimodal AI tool to improve success rates following liver transplantation.

The goal of the five-year national framework project with the University Health Network (UHN) and others is to understand the roadblocks to preventing fair access for all patients on the liver transplant waitlist, create an ethical, data-driven AI model framework to ensure equal access to donor organs going forward, and improve post-transplant outcomes.

“As part of developing an equitable AI-driven framework, we will include diverse voices in its development process. We will also analyze data on liver disease and transplants for all patients, regardless of race, socioeconomic status, sex and gender, to identify and address inequalities,” says Sharma, who leads York’s IMPACT-AI lab and is a scientist at UHN.

“Our AI tools will not only help to predict but also improve long-term health outcomes for transplant patients by reducing disparities.”

Some three million Canadians from all sectors of society are affected by liver disease. Although transplants can be life saving for those with end-stage liver disease, access is not equal and about 5,000 patients die from end-stage liver disease annually.

“Building trust and understanding around the new AI technology is an important piece of our project. By talking with patients, doctors and technology experts about what our AI model will do and how it can improve the process and the outcome, it can help ensure the adoption and clinical success of the framework,” says Sharma, who earned a 2025 Petro-Canada Emerging Innovator Award and a New Frontiers in Research Fund grant to develop genomic data-driven generative AI for pancreatic cancer.

“Ensuring the framework model is ethical from the beginning is key in reversing inequities to liver transplants some patients currently experience across Canada.”

"We will also analyze data on liver disease and transplants for all patients, regardless of race, socioeconomic status, sex and gender, to identify and address inequalities."

However, once a patient receives a liver transplant there is a high potential for serious complications. Up to 25 per cent of recipients will develop graft fibrosis or scarring from immunosuppressant medications or through organ rejection. Sharma’s second five-year project with UHN hopes to address this by developing a multimodal AI tool to predict patients at high risk of graft scarring.

“Our AI tools will not only help to predict but also improve long-term health outcomes for transplant patients by reducing disparities.”

Sharma says they previously used clinical and laboratory data from about 2,000 transplant recipients to develop a mathematical model to diagnose the condition. They will now expand the model’s capabilities using pathology and ultrasound imaging data so that it can also predict the future risk of scarring. The hope is it will lead to earlier diagnosis, and the development of better prevention and treatment strategies to improve outcomes.

The work of both projects are designed to have clinical benefits in hospitals and transplant centres that will result in improved and more equitable patient care. Sharma is also co-first author on a recent paper in the journal , which highlights the team’s work with GraftIQ, a neural network model designed to be a non-invasive diagnostic tool for liver graft injury.

These are some of the ways York researchers are capitalizing on the ability of well-designed, ethical and safe AI tools to provide real health benefits to patients, now and into the future.

The post Tools of the trade appeared first on Ascend Magazine.

A considerable feat, given the fact that satellites transmit signals from more than 20,000 kilometres away in space and smartphone reception can be quite weak (a phone’s antenna costs less than a dollar to manufacture).

“Because these satellites are so high in orbit and a consumer product like a smartphone uses low-grade and low-cost hardware, the great engineering challenge is to find ways to make everyday technology more precise,” explains Sunil Bisnath, a professor of geomatics engineering, whose research team also includes PhD students Yi Ding and Jiahuan Hu.

For the trio, that meant “squeezing” as much information from the satellite data as possible, and as much as a smartphone’s computing processor could handle.  

“Professional-grade GPS equipment that can measure millimetre distances costs tens of thousands of dollars. Smartphones are not designed to function at such a high level,” said Bisnath. “Our positioning technique to fill in missing data gaps was able to significantly improve the accuracy and quality of the measurements.”

Their findings, published this year in , detail their method, which involved manipulating specific types of satellite data called pseudorange and carrier-phase measurements, multiplying the speed of light by the time these signals have taken to travel from the satellites to the smartphone receiver.

The researchers used York’s Keele Campus as a living lab to test their work, mounting a GPS-enabled smartphone on a car dashboard and driving on various roads at and around the University and on 400-series highways.

Currently, Bisnath and his team continue to refine their technique, working to enhance its precision even further, while exploring potential partnership interest from industry.

This latest innovation builds on more than 30 years of research by Bisnath, who began studying GPS in the early 1990s upon the suggestion of one of his professors.

“I didn’t know what GPS was at the time, but now it’s become so pervasive in our daily lives,” said Bisnath. “From getting your dinner delivered on an app to following package deliveries online to conducting transactions with your bank card, GPS plays an integral role in how modern society works.

“So what I thought was a one-time project turned out to be an entire career.”

The post Lassonde research boosts accuracy of GPS in smartphones appeared first on Ascend Magazine.

With an average of 74 cyclists killed every year in Canada, according to Statistics Canada, Jadidi decided to investigate how modern technologies could help make the cycling experience safer and less stressful. 

In a paper titled Improving Cyclists’ Safety Using Intelligence Situational Awareness System, published this year in Sustainability, Jadidi and her co-authors (Gunho Sohn, associate professor in geomatics engineering, and PhD candidate Amir Nourbakhsh) described how they were able integrate information from disparate sources into a mobile app that delivers updated information in real-time to Toronto cyclists via voice alerts.

“Many technology companies have worked with the car industry, so we have lots of sensors embedded in the car like back-up cameras and safety sensors,” she points out. “But the bike has not really changed. We thought about how we could build a system using the current infrastructure without adding more tech and be accessible to most people, so we focused on the phone.”

Jadidi’s team created a solution that analyzes location data, historical collision data, weather information, real-time current road conditions and traffic patterns to determine whether cyclists are at higher risk of collisions as they move around the city. 

“Information is a power,” she says. “When you have this power, you can make better and informed decisions. If a cyclist receives a warning telling them they’re entering a high-risk area, they can change their behaviour, go slower, or stop and take a different and safer route.”

Jadidi is also currently using quantum computing to analyze how to optimize bike sharing systems to better anticipate supply and demand by distributing bikes where they are most needed in real-time. She explains that she’s passionate about supporting cycling as a safe, accessible, and sustainable way to move around cities. 

“The bike can be very easily streamlined into the transit system, and it’s easy to connect these two modes of transportation,” she points out. “It’s a great way to get around the city without taking a car and making more pollution”—that is, if the safety issues can be addressed. 

With the source code for Jadidi’s safety application freely available on GitHub, she’s hopeful that it will be adapted by other developers to create safer streets that support cyclists as well as drivers. 

“Cycling is sustainable, inclusive and accessible, with a lower cost than a car,” she says. “We have the technology to deliver the information cyclists need to be safer. So why not do it?”

The post York engineers develop mobile app to improve the safety of city cycling appeared first on Ascend Magazine.

While working on research in developing optimization algorithms, Seyyed-Kalantari’s life was derailed by a medical misdiagnosis that took two years to resolve. It was an agonizing experience, but it also inspired her to find a way to prevent the same thing from happening to others. 

“I saw the impact of having an under-diagnosis in my personal life,” she says. “I remember wishing that my research could help patients reduce pain.” 

Seyyed-Kalantari found a way to do just that during her post-doctoral fellowships at the Vector Institute and the University of Toronto, where she began investigating inaccuracies in AI diagnostics—work that she continues to pursue at York. 

And she’s uncovered some troubling findings that have caught even her by surprise.

In a paper published in Nature Medicine, Seyyed-Kalantari, as the lead author, examined data from multiple sources in the U.S. and discovered that AI-driven screening tools of chest X-rays had a concerning rate of under-diagnosis among underserved patient populations. 

“Historically vulnerable subpopulations—for example, Black, Hispanic, female and low-income patients—are suffering more from AI mistakes in these algorithms compared to other sub-populations,” 

she explains, noting that under-diagnoses are particularly harmful. “Upon deployment of such AI models, these patients were wrongly diagnosed as healthy. That means they may not have received any treatment in a timely manner and were sent home without further assessments.”

Even radiologists were taken aback, she added. “They said that when reviewing patient results, they don’t know anything about the patient’s race. They are sitting in a dark room reviewing the images and asking themselves ‘How can we be unfair to a patient that we have never seen?’” 

So, Seyyed-Kalantari and her multi-disciplinary, multi-institutional team delved further, looking into whether AI could determine the race of a patient from X-rays, CT scans and mammographic images alone. The results, published in The Lancet Digital Health, were astonishing.

“With a very high accuracy, AI models can determine the race of the patient by just looking at medical images,”

says Seyyed-Kalantari. “Everybody was surprised, and it was alarming. We don't know what AI is doing with this information. While we find that AI models can detect the race of patients, we find at the same time that AI is behaving against some races.”

The question now is: how is it happening? And what are the repercussions? 

Seyyed-Kalantari is actively looking for answers as she delves deeper into her work at Lassonde. In the meantime, she urges caution in embedding AI into healthcare. 

“Some AI algorithms have received FDA approval in the U.S. for applications in radiology. But to the best of my knowledge, they haven’t proven that the
algorithms are fair,” she warns. 

“If we’re deploying these algorithms and using them for disease diagnoses -and we’re not sure if they’re fair or not -this could harm some groups in our society.”

This concern underscores why research like Seyyed-Kalantari’s is so important, and how further research in this field can help ensure that the healthcare of tomorrow is truly fair and equitable. 

The post Uncovering racial bias in AI appeared first on Ascend Magazine.