Technology | 07.06.22
Artificial Intelligence May Diagnose Dementia as Accurately as Clinicians
by United Press International
A newly published study suggests artificial intelligence (AI) could help diagnose dementia with clinician-level accuracy. The researchers used machine learning to craft computer models that could absorb large datasets that might be collected during a typical work-up of a patient with suspected dementia. Included were results of neuro-psychological and functional testing, medical history, physical exams, demographics, and magnetic resonance imaging scans of patients from the United States and Australia. This data was fed to a neural network "trained to elicit disease-specific signatures from this vast set of inputs," according to a Boston University news release. Moreover, Boston University Professor Vijaya Kolachalama said 17 neurologists and seven radiologists trained in neuroimaging conducted a "head-to-head" comparative study with the AI models. The clinicians and models were assigned an identical set of 100 patients and asked to diagnose them using the same information, which yielded similar accuracy. Kolachalama said the model performed better at differentiating the type of dementia among patients who had been diagnosed.
Read more.