Search

LONDON, ON – A team of researchers at Lawson Health Research Institute is investigating whether an artificial neural network could be used to diagnose COVID-19. The AI system is being trained to learn and recognize patterns in ultrasound lung scans of patients with confirmed COVID-19 at London Health Sciences Centre (LHSC) by comparing them to ultrasound scans of patients with other types of lung infections.

“Machines are able to find patterns that humans cannot see or even imagine. Lung ultrasound scans of patients with COVID-19 pneumonia produce a highly abnormal imaging pattern.  This pattern isn’t unique to COVID-19, and can be seen in other causes of pneumonia.  It is plausible, however, that there are details that distinguish COVID-19 at the pixel level that cannot be perceived by the human eye,” explains Dr. Robert Arntfield, Lawson Researcher and Medical Director of the Critical Care Trauma Centre at LHSC. “If we can train a neural network to learn and identify these unique characteristics among different scans, we can apply this AI to enhance the diagnostic power of portable ultrasound.”

Point-of-care ultrasound has become increasingly important for the care of critically ill patients and LHSC is a global leader in the use of this technology at the bedside. Lung ultrasound has proven to be effective in diagnosing different types of lung infections and illnesses, such as pneumonia, with a high degree of accuracy. The convenience, portability and low cost of using these machines has helped them become a standard bedside tool in emergency departments and intensive care units worldwide.

This research project is part of a grassroots effort by a small group of local clinicians to innovate and create technology to solve sophisticated problems with AI. With many of Dr. Arntfield’s team having a background in computer programming, they were able to code the neural network being tested. Minimal funding was required, with the project being driven largely by the urgency of COVID-19 coinciding with the recent creation of this clinical AI working group.

“Our research team has used AI to help improve diagnostics related to other parts of the body. This project is a great example of the unique ability we have here in London to be agile: that is, to identify a gap and move quickly towards finding a solution,” says Dr. Arntfield. “I am thrilled that we were able to move through the approval process quickly, and get our ideas working in such a short amount of time.”

-30-

Downloadable Media

Image

Dr. Robert Arntfield

Image

COVID-19 pneumonia ultrasound

Image

NON COVID-19 pneumonia ultrasound
 

See all Lawson Media Releases

LONDON, ON - Canadian researchers are the first to study how different patterns in the way older adults walk could more accurately diagnose different types of dementia and identify Alzheimer’s disease.  

A new study by a Canadian research team, led by London researchers from Lawson Health Research Institute and Western University, evaluated the walking patterns and brain function of 500 participants currently enrolled in clinical trials. Their findings are published today in Alzheimer's & Dementia: The Journal of the Alzheimer's Association. 

“We have longstanding evidence showing that cognitive problems, such as poor memory and executive dysfunction, can be predictors of dementia. Now, we’re seeing that motor performance, specifically the way you walk, can help diagnose different types of neurodegenerative conditions,” says Dr. Manuel Montero-Odasso, Scientist at Lawson and Professor at Western’s Schulich School of Medicine & Dentistry.  

Dr. Montero-Odasso is world renowned for his research on the relationship between mobility and cognitive decline in aging. Leading the Mobility, Exercise and Cognition (MEC) team in London, he is pioneering novel diagnostic approaches and treatments to prevent and combat early dementia.  

This study compared gait impairments across the cognitive spectrum, including people with Subjective Cognitive Impairment, Parkinson’s Disease, Mild Cognitive Impairment, Alzheimer’s disease, Lewy body dementia and Frontotemporal dementia, as well as cognitively healthy controls.  

Four independent gait patterns were identified: rhythm, pace, variability and postural control. Only high gait variability was associated with lower cognitive performance and it identified Alzheimer’s disease with 70 per cent accuracy. Gait variability means the stride-to-stride fluctuations in distance and timing that happen when we walk.  

“This is the first strong evidence showing that gait variability is an important marker for processes happening in areas of the brain that are linked to both cognitive impairment and motor control,” notes Dr. Frederico Perruccini-Faria, Research Assistant at Lawson and Postdoctoral Associate at Western’s Schulich School of Medicine & Dentistry, who is first author on the paper. “We’ve shown that high gait variability as a marker of this cognitive-cortical dysfunction can reliably identify Alzheimer’s disease compared to other neurodegenerative disorders.”  

When cognitive-cortical dysfunction is happening, the person’s ability to perform multiple tasks at the same time is impacted, such as talking while walking or chopping vegetables while chatting with family.  

Having gait variability as a motor marker for cognitive decline and different types of conditions could allow for gait assessment to be used as a clinical test, for example having patients use wearable technology. “We see gait variability being similar to an arrhythmia. Health care providers could measure it with patients in the clinic, similar to how we assess heart rhythm with electrocardiograms,” adds Dr. Montero-Odasso.  

This study was primarily funded by the Canadian Consortium on Neurodegeneration in Aging (CCNA), a collaborative research program tackling the challenge of dementia and other neurodegenerative illnesses. The CCNA was supported by a grant from the Canadian Institutes of Health Research 

-30-

See all Lawson Media Releases