According to a new study, MRI scans and an artificial intelligence technique can be used for detecting mild cognitive disorders that progress later causing Alzheimer's disease. The study took place at the University Hospital of Geneva in Switzerland; its findings are highlighted online and will appear in the December printed issue of the journal Radiology. Dr. Sven Haller, a radiologist in the department of diagnostic and interventional neuroradiology, the lead author of the study, said "Medication against Alzheimer is presumably most effective when given early in the disease progress. Our results help to identify subjects at risk for cognitive decline at an early stage, which might result in an earlier and more specific treatment."
MRI and cognitive impairments.
During the study, Dr. Haller and his team reviewed MRI scans of 35 healthy participants, their age average was 64. They also checked scans of 69 other participants; their age average was 65, with mild cognitive impairment. All the involved individuals in the second group were identified to have mild cognitive impairment following the conduction of several neuropsychological tests. In order to detect patients who had stable or progressing impairments, these tests took place again one year later. Dr. Haller and his team used a special imaging techniques named susceptibility-weighted MRI to brain image the participants in the study. It was noted that patients indentified with mild cognitive impairment showed an increased number of small blood leaks, micorbleeds, in their brain blood vessels than the healthy individuals. The researching team reported microbleeds in 33% of the participants with stable mild cognitive impairment, in addition to 54% in those with progressive mild cognitive impairment. One the other hand, health individuals showed microbleeds in only 14% of them.
Moreover, researchers reviewed the MRI scans using an artificial intelligence technique named Support Vector Machines (SVM). The technique is used to determine patterns within a group and provide classifications. It was reported that the SMV technique was able to identify and differentiate, with 85% accuracy, patients who had progressive and other who had stable mild cognitive impairment.