Latest news with #McGill University
National Post
3 hours ago
- Health
- National Post
McGill researchers develop AI that predicts respiratory illness before symptoms show
Researchers at McGill University say they developed an artificial intelligence platform that can predict when someone is about to come down with a respiratory tract infection before they start to feel sick. Article content In what researchers are calling a 'world first,' the study involved participants who wore a ring, a watch and a T-shirt, all of which were equipped with sensors that recorded their biometric data. By analyzing the data, researchers were able to accurately predict acute systemic inflammation — an early sign of a respiratory infection such as COVID-19. Article content Article content Article content Published in The Lancet Digital Health, the study says the AI platform can one day help doctors address health problems much earlier than they normally would, particularly in patients who are fragile and for whom a new infection could have serious consequences. It could also potentially reduce costs for the health-care system by preventing complications and hospitalizations. Article content Article content 'We were very interested to see if physiological data measured using wearable sensors … could be used to train an artificial intelligence system capable of detecting an infection or disease resulting from inflammation,' explained the study's lead author, Prof. Dennis Jensen of McGill University's department of kinesiology and physical education. Article content 'We wondered if we could detect early changes in physiology and, from there, predict that someone is about to get sick.' Article content Jense says the AI model his team created is the first in the world to use physiological measures — including heart rate, heart rate variability, body temperature, respiratory rate, blood pressure _ rather than symptoms, to detect a problem. Article content Article content Acute systemic inflammation is a natural defence mechanism of the body that usually resolves on its own, but it can cause serious health problems, especially in populations with pre-existing conditions. Article content Article content 'The whole idea is kind of like an iceberg,' Jensen said. 'Kind of when the ice cracks the surface, that's like when you're symptomatic, and then it's too late to really do much to treat it.' Article content During the study, McGill researchers administered a weakened flu vaccine to 55 healthy adults to simulate infection in their bodies. The subjects were monitored seven days before inoculation and five days after. Article content Participants wore a smart ring, smart watch, and a smart T-shirt simultaneously throughout the study. As well, researchers collected biomarkers of systemic inflammation using blood samples, PCR tests to detect the presence of respiratory pathogens, and a mobile app to collect symptoms reported by participants. Article content In total, more than two billion data points were collected to train machine learning algorithms. Ten different AI models were developed, but the researchers chose the model that used the least amount of data for the remainder of the project. The chosen model correctly detected nearly 90 per cent of actual positive cases and was deemed more practical for daily monitoring.
CTV News
4 hours ago
- Health
- CTV News
McGill University team develops AI that can detect infection before symptoms appear
Participants wore a smart ring, a smart watch, and a smart T-shirt that monitored multiple physiological parameters and activities. In the photo, an Apple Watch in 2015 in Tokyo. (Koji Sasahara, File/AP Photo) MONTRÉAL — Researchers at McGill University say they developed an artificial intelligence platform that can predict when someone is about to come down with a respiratory tract infection before they start to feel sick. In what researchers are calling a 'world first,' the study involved participants who wore a ring, a watch and a T-shirt, all of which were equipped with censors that recorded their biometric data. By analyzing the data, researchers were able to accurately predict acute systemic inflammation — an early sign of a respiratory infection such as COVID-19. Published in The Lancet Digital Health, the study says the AI platform can one day help doctors address health problems much earlier than they normally would, particularly in patients who are fragile and for whom a new infection could have serious consequences. It could also potentially reduce costs for the health-care system by preventing complications and hospitalizations. 'We were very interested to see if physiological data measured using wearable sensors … could be used to train an artificial intelligence system capable of detecting an infection or disease resulting from inflammation,' explained the study's lead author, Prof. Dennis Jensen of McGill University's department of kinesiology and physical education. 'We wondered if we could detect early changes in physiology and, from there, predict that someone is about to get sick.' Jense says the AI model his team created is the first in the world to use physiological measures — including heart rate, heart rate variability, body temperature, respiratory rate, blood pressure — rather than symptoms, to detect a problem. Acute systemic inflammation is a natural defence mechanism of the body that usually resolves on its own, but it can cause serious health problems, especially in populations with pre-existing conditions. 'The whole idea is kind of like an iceberg,' Jensen said. 'Kind of when the ice cracks the surface, that's like when you're symptomatic, and then it's too late to really do much to treat it.' During the study, McGill researchers administered a weakened flu vaccine to 55 healthy adults to simulate infection in their bodies. The subjects were monitored seven days before inoculation and five days after. Participants wore a smart ring, smart watch, and a smart T-shirt simultaneously throughout the study. As well, researchers collected biomarkers of systemic inflammation using blood samples, PCR tests to detect the presence of respiratory pathogens, and a mobile app to collect symptoms reported by participants. In total, more than two billion data points were collected to train machine learning algorithms. Ten different AI models were developed, but the researchers chose the model that used the least amount of data for the remainder of the project. The chosen model correctly detected nearly 90 per cent of actual positive cases and was deemed more practical for daily monitoring. On their own, Jensen said, none of the data collected from the ring, watch, or T-shirt alone is sensitive enough to detect how the body is responding. 'An increase in heart rate alone may only correspond to two beats per minute, which is not really clinically relevant,' he explained. 'The decrease in heart rate variability can be very modest. The increase in temperature can be very modest. So the idea was that by looking at … several different measurements, we would be able to identify subtle changes in physiology.' The algorithms also successfully detected systemic inflammation in four participants infected with COVID-19 during the study. In each case, the algorithms flagged the immune response up to 72 hours before symptoms appeared or infection was confirmed by PCR testing. Ultimately, the researchers hope to develop a system that will inform patients of possible inflammation so they can contact their health-care provider. 'In medicine, we say that you have to give the right treatment to the right person at the right time,' Jensen said. By expanding the therapeutic window in which doctors can intervene, he added, they could save lives and achieve significant savings by avoiding hospitalizations and enabling home management of chronic conditions or even aging. 'In a way, we hope to revolutionize personalized medicine.' This report by The Canadian Press was first published July 30, 2025. By Jean-Benoit Legault, The Canadian Press
The Guardian
5 days ago
- Health
- The Guardian
Surrogates at greater risk of new mental illness than women carrying own babies, study finds
Surrogates have a greater chance of being newly diagnosed with a mental illness during and after pregnancy than women who carry their own offspring, researchers have found. In addition, regardless of how they conceived, women with a previous record of mental illness were found to have a higher risk of being diagnosed with such conditions during and after pregnancy than those without. While laws around surrogates, or 'gestational carriers', vary around the world, the practice is booming. According to Global Market Insights, the market is expected to grow from $27.9bn (£20.8bn) in 2025 to $201.8bn (£150.2bn) in 2034. 'Our findings underscore the importance of adequate screening and counselling of potential gestational carriers before pregnancy about the possibility of a new-onset mental illness, or exacerbation of a prior mental illness during or after pregnancy,' said Dr Maria Velez, the first author of the research, from McGill University in Canada. 'As well, the provision of support during and after pregnancy may be particularly important for gestational carriers.' Writing in the journal Jama Network Open, Velez and colleagues report how they analysed data from 767,406 births in Ontario that occurred between 1 April 2012 and 31 March 2021. Of these, 748,732 involved unassisted conceptions, 758 involved surrogacy, and the others involved IVF in mothers who carried their own babies. Velez said the vast majority of surrogacy cases in Canada involved the surrogate being unrelated to the child, meaning the surrogate's eggs were not used in conception. Among those excluded from this initial analysis were women with a record of mental illness prior to the estimated date of conception. The team analysed the number of women in each group who received a diagnosis of a new-onset mental illness since the estimated date of conception, such as anxiety disorder, mood disorder, self-harm or psychosis. These diagnoses occurred in 236 surrogates, 195,022 women who had an unassisted conception and 4,704 women who had received IVF. After accounting for factors such as age, income, smoking and number of children, this corresponded to a 43% and 29% higher incidence rate of new mental illness per 100 people per year of follow-up in surrogates compared with women who had an unassisted conception or IVF, respectively. For all three groups, mood or anxiety disorder was the most common diagnosis, while median time from conception to diagnosis was similar, at about two and a half years. The researchers found the risk of new mental illness remained elevated in surrogates, but to a lesser degree, when compared with women who had an unassisted conception but no longer lived with their child a year after the birth. 'The finding might suggest that some gestational carriers may experience grief from relinquishing their newborn, like that described after adoption or removal of the child into foster care – something that needs further studies,' said Velez. The team then carried out further analyses that included women with a previous record of mental illness and found all groups in this category had a higher rate of new-onset mental illness than those with no previous record. Despite Canada requiring would-be surrogates to undergo psychological assessments, the results revealed 19% of surrogates in the study had a documented diagnosis of mental illness before pregnancy. The study follows previous research by the team that found surrogates were more likely to experience complications including severe postpartum haemorrhage and severe pre-eclampsia. Dr Zaina Mahmoud, an expert on the socio-legal aspects of surrogacy at the University of Liverpool, in England, who was not involved in the work, said further research was needed to explore whether the greater risk of new mental illness in surrogates was down to the pregnancy itself, and the mechanisms at play. '[The researchers are] not addressing why or how surrogates have these emotional trajectories,' she said, adding that the team had used very broad definitions of mental illness. 'They hypothesise that grief from relinquishing the infant may contribute, but they don't actually measure that grief.' But Mahmoud backed the call for greater screening and support for potential surrogates, saying the work suggested support should last for more than two years after the birth. The studies 'really highlight the need for robust information and consent procedures', she said.
CTV News
21-07-2025
- General
- CTV News
Plane crashes and hijackings: Are aerial incidents rising in Canada? Experts weigh in
A seaplane crash at an Ontario lake and a plane hijacking at a B.C. airport have prompted questions about aircraft safety and airport security — but data shows airplane accidents are declining on average, and experts say there may be too many challenges to get security at small- to medium-sized airports up to the level they need to be. Transportation Safety Board of Canada (TSB) data from the last five years show there have been fewer than 200 'plane accidents' each year — with 193 in 2024, 181 in 2023, 167 in 2022, 192 in 2021 and 171 in 2020. That averages roughly 181 plane crashes per year over that span. But the previous decade — from 2010 to 2019 — saw an average of 251 plane accidents per year, significantly higher than Canada has seen more recently. 'We have an increase in the quality of pilots, pilots are much more rigorously trained and inspected, and that's done by Transport Canada and by instructors,' said John Gradek, from McGill University's aviation management school. 'More airplanes are flying, but a reduction in incidents, which is good news.' Investigators are still trying to determine the cause of a seaplane crash this week, when a 16-year-old died at Lake Scugog, Ont., after a small plane collided with the dock he was standing on. The teen died at the scene, while the pilot was taken to hospital with minor injuries. TSB investigators have not yet confirmed what contributed to the crash but said alcohol was not a factor. TSB told CTV News in an email that investigators were back on scene Sunday and that the aircraft had been examined. 'The aircraft will be transported to a secure location in case they need to look at it again. Interviews with witnesses have been carried out,' said TSB spokesperson Nic Defalco. Gradek said the TSB's role in providing recommendations to Transport Canada after crash investigations has played a major role in improving pilot training and safety measures, helping reduce crashes overall. 'What Transport Canada has done in the last few years is really take note of TSB recommendations on small airplanes and really instructed their inspectors to be more vigilant — in terms of the aspects the TSB might have reported on, things like training, like the number of hours. Particularly, floatplanes are very fickle in how you fly them,' he added. Hijacking at B.C. airport sparks security debate A plane hijacking from the Victoria Flying Club in B.C. has also raised questions about increasing security at smaller airports across Canada — which experts say is ideal in theory, but nearly impossible in practice. 'You certainly want to increase security reasonably where you can, but I think you would be hard-pressed to impose a uniform level of security in the general aviation world because there are so many airports. A lot of them are out in the middle of nowhere, some of them have very little activity — it would be really, really challenging to come up with security that we think of in the commercial world as consistent,' said Steven Green, a retired Boeing 737 captain and accident investigator, in a Zoom interview with CTV News Sunday. CTV News reached out to more than a dozen small- to medium-sized airports across the country from Thursday to Sunday. While some did not respond to the request, others said they have no plans to change security measures following the hijacking incident in B.C. 'Following any incident, we conduct an internal review to assess our response and identify areas for improvement,' said Linsday Gaunt, Vice President of Revenue Strategy and Business Development at Victoria Airport, in an email to CTV News. 'Should Transport Canada make any recommendations as a result of this investigation, we will work with them to support implementation as appropriate.'
Yahoo
13-07-2025
- Science
- Yahoo
Professor deploys high-tech drones that could transform the food we eat: 'Gains we've only dreamed of'
One researcher aims to make in-depth studies of plant characteristics more accessible, enabling breeders to make informed decisions when developing the most resilient crops for their specific region. Dr. Valerio Hoyos-Villegas, an assistant professor at Michigan State University, adjunct professor at Montreal's McGill University, and former president of the North American Plant Phenotyping Network, has been deploying sensor-laden drones to help accomplish this mission, as Seed World reported. In today's changing climate, it's important to develop the most resilient plant varieties so they can survive and even prosper in the face of rising global temperatures and increased drought. That requires more than just genetic predictions; it takes data. Phenomics – the science of measuring traits – helps bridge the gap between those predictions and the real world, Seed World explained. "Breeding is a resource management game," Hoyos-Villegas told the outlet. "Phenomics gives us the precision tools to manage those resources better – and to unlock genetic gains we've only dreamed of." Seed World reported that, after analyzing over 100 scientific papers that included the phrase "affordable phenomics," Hoyos-Villegas' team began to see certain recurring terms: breeding, genetics, unmanned aerial vehicles (UAVs), yield, and drought. It was clear that affordable phenomics was seen as a tool in selecting breeds with high yields and drought resistance, but affordability can be a relative term. The challenge was creating scalable solutions for breeders, regardless of their resources. The most accessible way to study phenomics is through the use of UAV-based imaging, which uses RGB or multispectral cameras to capture thousands of data points in just minutes, the report explained. High-resolution images can be used to track canopy temperature — which relates to water use — and monitor plant height and growth rates over time. This data helps breeders find the very best plants for increased yields and drought tolerance. Which of these groups has the biggest role to play in reducing food waste? Grocery stores Restaurants Individuals The government Click your choice to see results and speak your mind. "Increasing selection intensity is the key to faster progress," Hoyos-Villegas told Seed World. "Affordable phenomics makes that possible." According to the United Nations, the global population is predicted to grow to 9.6 billion people by 2050, and food production, especially more eco-friendly plant-based options, must be increased by 60% to meet that demand. Other researchers are already using drones to monitor corn and wheat crops to help optimize production and find strains that are best suited for this changing world. Hoyos-Villegas believes that making data collection more accessible to breeders across the world will help each region improve crop selection to address local needs in a grassroots movement. "We're not just chasing yield," Hoyos-Villegas told Seed World. "We're chasing access. And that means building tools that work for everyone." Join our free newsletter for easy tips to save more and waste less, and don't miss this cool list of easy ways to help yourself while helping the planet.
