A machine-learning algorithm can diagnose Alzheimer’s disease with a single brain scan, according to a new study.
The study found that the MRI algorithm can predict whether a person has Alzheimer’s or not with 98% accuracy. The study also found that the algorithm can differentiate between early and late-stage Alzheimer’s patients with an accuracy of 79%.
“Currently, no other simple and widely available methods can predict Alzheimer’s disease with this level of accuracy, so our research is an important step forward,” said lead researcher Eric Aboagye in a media release.
Although there is no cure for Alzheimer’s, getting a diagnosis quickly at an early stage helps patients.
To diagnose someone with Alzheimer’s, many tests must be taken, including brain imaging, cognitive tests, blood tests, and tests to look for biomarkers or hallmarks of the disease.
“Many patients who present with Alzheimer’s at memory clinics also have other neurological conditions, but even within this group our system could pick out those patients who had Alzheimer’s from those who did not,” said Aboagye.
The researchers found the algorithm identified features previously not associated with Alzheimer’s in the cerebellum—the part of the brain that maintains balance posture—and the ventral diencephalon, which is linked to the sensory and motor functions and sleep-wake cycles.
“Although neuroradiologists already interpret MRI scans to help diagnose Alzheimer’s, there are likely to be features of the scans that aren’t visible, even to specialists,” said Dr. Paresh Malhotra, a consultant neurologist at Imperial College Healthcare NHS Trust and a researcher in Imperial’s Department of Brain Sciences.
“Using an algorithm able to select texture and subtle structural features in the brain that are affected by Alzheimer’s could really enhance the information we can gain from standard imaging techniques,” added Malhotra.
The new approach requires just one MRI brain scan to be taken on a standard 1.5 Tesla machine. The 1.5 Tesla machine is commonly found in most hospitals.
The study was published in the Nature Portfolio journal, Communications Medicine, and funded through the National Institute for Health and Care Research (NIHR), Imperial Biomedical Research Centre, and the Medical Research Council.