Today’s report on AI of retinal vessel images to help predict the risk of heart attack and stroke, from over 65,000 UK Biobank participants, reinforces a growing body of evidence that deep neural networks can be trained to “interpret” medical images far beyond what was anticipated. Add that finding to last week’s multinational study of deep learning of retinal photos to detect Alzheimer’s disease with good accuracy. In this post I am going to briefly review what has already been gleaned from 2 classic medical images—the retina and the electrocardiogram (ECG)—as representative for the exciting capability of machine vision to “see” well beyond human limits. Obviously, machines aren’t really seeing or interpreting and don’t have eyes in the human sense, but they sure can be trained from hundreds of thousand (or millions) of images to come up with outputs that are extraordinary. I hope when you’ve read this you’ll agree this is a particularly striking advance, which has not yet been actualized in medical practice, but has enormous potential.
Author(s): Eric Topol
Publication Date: 4 Oct 2022
Publication Site: Eric Topol’s substack, Ground Truths
Patients with dementia are at higher risk for Covid-19 and are more likely to have worse outcomes, according to a new study published today.
The study, led by Case Western Reserve University researchers, reviewed electronic health records of 61.9 million adults in the United States and found that the risk for contracting Covid-19 was twice as high for people with dementia compared to the general population.
The risk was even greater still for African Americans with dementia, who were found to be close to three times as likely to be infected with Covid-19.
The study, which was published in the journal Alzheimer’s & Dementia: The Journal of the Alzheimer’s Association, also found that certain types of dementia had a greater risk than others.
The early prognosis of high-risk older adults for amnestic mild cognitive impairment (aMCI), using noninvasive and sensitive neuromarkers, is key for early prevention of Alzheimer’s disease. A recent study, published in the Journal of Alzheimer’s Disease, by researchers at the University of Kentucky establishes what they believe is a new way to predict the risk years before a clinical diagnosis. Their work shows that direct measures of brain signatures during mental activity are more sensitive and accurate predictors of memory decline than current standard behavioral testing.
“Many studies have measured electrophysiological rhythms during resting and sleep to predict Alzheimer’s risk. This study demonstrates that better predictions of a person’s cognitive risk can be made when the brain is challenged with a task. Additionally, we learned that out of thousands of possible brain oscillation measures, left-frontal brainwaves during so-called working memory tasks are good predictors for dementia risk,” explained lead investigator Yang Jiang, associate professor of behavioral sciences and an affiliated faculty member at the Sanders-Brown Center on Aging.
Author(s): University of Kentucky (it’s a press release)