Alzheimer’s Researchers Log Better Results with Advanced Algorithm
Kristin Houser from freethink.com writes that scientists have developed an artificial intelligence algorithm that’s better than most neurologists at making an Alzheimer’s diagnosis — a development with the potential to improve healthcare for countless people. There is no cure for Alzheimer’s disease.
There’s no one test for Alzheimer’s and symptoms vary from patient to patient, making it incredibly difficult to diagnose.
Doctors must consider the patient’s cognition, family history, MRI results and other variables. Two doctors can look at the data and come up with opposing opinions for the treatment of the patient. This new algorithm eliminates some subjectivity.
To train the algorithm to make an accurate Alzheimer’s diagnosis, scientists fed it data from the Alzheimer’s Disease Neuroimaging Initiative. This data included patients’ MRI scans, basic demographic information, and scores from a test used to measure cognitive impairment.
“If computer models can detect the disease accurately, lives can be saved,” said Vijaya Kolachalama, a researcher.
According to the team’s paper, published in the journal Brain, the AI “displayed good predictive performance, yielding high and consistent values on all the test datasets.”
The researchers averaged the neurologists’ accuracy and found that the AI was slightly more accurate than the neurologists. Even being slightly more accurate, means a lot in the treatment of this disease. The use of AI could reduce the prevalence of errors during the diagnostic process, which the scientists say result in an estimated 40,000 to 80,000 deaths per year.
And of course, AI is finding even more success in helping other areas of the medical field with a diagnosis of data that is more accurate and produced in far less time. AI won’t replace your favorite doctor, but it will help to make your favorite doctor better.
read more at freethink.com