Listen to this story
Artificial intelligence can be used to detect Alzheimer’s disease and other similar dementias, according to a new scientific experiment.
Published by the Eureka Alert scientific journal, the experiment was conducted by researchers across universities such as the University of Miami Miller School of Medicine, the Regenstrief Institute and the IU School of Medicine, amongst others. For the experiment, they included 7,200 participants from the ages of 65 and over. The criteria for the study included a minimum of one appointment at a primary care practice in the last year.
Their information was then put through an artificial intelligence tool known as the passive digital marker. With the machine, the patient’s information is processed to filter and select files that feature wording relating to potential Alzheimer’s disease symptoms. Factors relating to Alzheimer’s disease include memory loss, vascular issues, difficulty finding words, dealing with difficult tasks and issues with planning.
“Between 50 to 80 percent of dementia cases are unrecognized by the healthcare system in the U.S. And, if you include patients living with mild cognitive impairment, that number might actually climb to higher than 80 percent of cases that are not recognized,” said lead author and member of the Refendtrief Institute, Malaz Boustani, M.D.,MPH, per a news release.
“Over the past 20 years we have developed, validated and have been operating a comprehensive collaborative care model for dementia that reduces the disease burden for the patient, reduces caregiver stress and reduces inappropriate hospitalizations, keeping people living at home longer and lowering overall costs to them and to the healthcare system.”
The experiment will span across two trials, with the current trial already being conducted in Indianapolis. The focus of the study will be on members of the Black community who live in mostly urban places.
Of all racial and ethnic groups, Black Americans are among the patients that report higher rates of Alzheimer’s disease and other similar dementias. According to a 2021 report by the U.S. National Institute of Health, Black patients have an increased 1.5 to double the chance of developing one of these illnesses when compared to white Americans.
Despite this, they have a lower diagnosis rate, recording a rate of just 26.8%, while white Americans recorded one of 36.1%.
Nonetheless, the new trials of an AI-led diagnosis practice is reflective of increased testing of how this technology can be used in medicine. Since 2018, many institutes, such as Cedars-Sinai, have attempted to put devices into practice.
Still, as of now, only a select few of assistive algorithms have received a seal of approval for the U.S. Food and Drug Administration, with no universal protocols being set.