Posted on Dec 22, 2019, 2 p.m.
From November 20 to December 4, 2019 The Radiological Society of North American held their annual meeting of Human Insight/Visionary Medicine at McCormick Place in Chicago, IL; the next one will be the 106th Scientific Assembly and Annual Meeting which will be held Nov. 29- Dec. 4, 2020 at the same location.
RSNA works to provide educational resources as well as hosts conferences and publishes the peer reviewed journals Radiology and RadioGraphics. The annual meeting hosts a variety of scientific and applied science presentations, as well as original and innovative, educational exhibits, and quality improvement reports.
Among the impressive presentations and exhibits at the RSNA meeting was technology using AI to detect Alzheimer’s disease. Despite all of the advances in medicine and technology there still is no cure for this debilitating and brain wasting disease. This technology utilizes artificial intelligence to scan as well as read MRI scans to detect evidence of the disease at an early stage. The AI deep machine learning algorithms can detect cognitive decline in scans, genetics and clinical data to predict whether findings will lead to Alzheimer’s disease before symptoms appear.
Similar to that at the RSNA, AI developed at the University of Toronto and the Center for Addiction and Mental Health trained their Al deep learning algorithm with data from the Alzheimer’s Disease Neuroimaging Initiative through the National Institutes of Health’s National Institute on Aging using data from over 800 geriatric patients ranging from healthy to mild cognitive impairment to Alzheimer’s disease. Their algorithm was found to be able to accurately predict cognitive decline leading to AD in cohorts by analyzing brain scans, clinical data, and genetics by up to 5 years before symptoms appear; research was published in PLOS Computational Biology.
Research suggests that as many as 1 in 5 people aged 65+ will experience mild cognitive impairment which is marked by a slight decline in memory, language, or thought, and those affected are prone to forgetting appointments or losing concentration while in conversation. These people are also at a higher than average risk for more pronounced cognitive decline as well as Alzheimer’s disease, but in the majority symptoms don’t progress, presenting a challenge for diagnosing Alzheimer’s disease when it can be of best benefit for those affected to utilize the limited number of interventions and drugs.
As it stands diagnosis requires extensive evaluation, history, and testing including laboratory, neuropsychological, and neuroimaging scans which can take months of precious time, and even then it is still a challenge to deliver definitive diagnosis. Unfortunately this can only occur after death under a microscope to see how the disease has ravaged the brain architecture to cause tissues to degrade and shrink.
In the face of the many challenges developing technology to diagnose cases earlier and more precisely is extremely important. Based on research neural degeneration is suggested to begin many years before a person displays the first outward symptoms, but the changes are too subtle for most specialists to recognize. This is when a trained artificial intelligence algorithm can step in to recognize and help to predict these losses within a few moments saving valuable time.
While more data is needed to further advance this promising technology, many are waiting to see is if such technology will eventually make its way to the clinic to provide speedier diagnoses and better care for the millions of people who live with this progressive and currently irreversible degenerative mind wasting and debilitating disease.
Materials provided by:
Note: Content may be edited for style and length.
This article is not intended to provide medical diagnosis, advice, treatment, or endorsement.