Novel Brain Scan Diagnoses Alzheimer's and Progression with Impressive Accuracy
From suspicion to a confirmed diagnosis, a patient’s experience with Alzheimer’s disease begins with a painful “wait and see”. An important aspect of this troubling situation is the length of time associated with confirming a diagnosis through a series of imaging and performative tests. During the waiting period, patients are left speculating what the future might hold for them and their loved ones.
To shorten this painful window of time, researchers at Imperial College London in the United Kingdom have developed a novel diagnosis method demonstrating an impressively high rate of correct Alzheimer’s diagnosis and an equally impressive ability to determine the patient’s progression stage.
Using the new approach, the researchers achieved 98% accuracy in diagnosing whether a patient has Alzheimer's. For patients with the disease, the algorithm correctly defined the patient’s stage of progression in 78% of cases.
New developments occur daily for diagnosing Alzheimer’s, but this may be the first development that builds upon an imaging device that is already present in many hospitals and medical settings. Researchers at Imperial make use of a 1.5 Tesla MRI machine and a machine-learning algorithm to analyze regions, textures and structural features of a patient’s brain to determine whether they have Alzheimer’s, and if so, how far it has progressed. To do this, the brain is systematically divided into 115 regions with 660 different observable features.
Some of these new areas of interest include the cerebellum and the ventral diencephalon, which respectively facilitate coordination and sensory perception, among other responsibilities.
This research was funded through the National Institute for Health and Care Research Imperial Research Biomedical Research Centre. According to the Alzheimer’s Association, the current diagnosis approach includes a full phlebotomy work-up, lifestyle discussion, medication review and a neurological assessment that may include imaging of the brain. Imaging may show amyloid plaques, which build up as a patient loses the ability to dispose of amyloid proteins in a normal way, leading to cognitive decline. Diagnosis in the future might limit these requirements down to a simple MRI scan.
“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,” Eric Aboagye, lead researcher and professor of cancer pharmacology and molecular imaging at Imperial said.
“Many patients who present with Alzheimer’s at memory clinics do 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,” he said. “Waiting for a diagnosis can be a horrible experience for patients and their families. If we could cut down the amount of time they have to wait, make diagnosis a simpler process, and reduce some of the uncertainty, that would help a great deal. Our new approach could also identify early-stage patients for clinical trials of new drug treatments or lifestyle changes, which is currently very hard to do.”
This study made use of the Alzheimer’s Disease Neuroimaging Initiative, a global organization that has accumulated a large bank of Alzheimer’s information including imaging studies, biomarking and genetic information. These data sets are derived from patients in all stages of progression.
With a bank of information from more than 400 patients diagnosed with early to late-stage Alzheimer’s, the new method was put to the test, yielding impressive results. This published study indicates that Alzheimer’s continues to be more understood each day.