Alzheimer’s Treatment, Diagnosis Tool Arrive in 2021
Home > Health > Article

Alzheimer’s Treatment, Diagnosis Tool Arrive in 2021

Photo by:   Robina Weermeijer on Unsplash
Share it!
Miriam Bello By Miriam Bello | Senior Journalist and Industry Analyst - Fri, 11/19/2021 - 17:04

A digital version of the Clock-Drawing Test (CDT) was effective in identifying the early symptoms of Alzheimer’s in cognitively normal individuals, found researchers at the Massachusetts General Hospital (MGH).

Amyloid beta plaques associated with Alzheimer’s disease can appear in the brain as early as 15 to 20 years before clinical symptoms manifest, explains Linus Health, the developer company of the digital CDT. Early detection of cognitive impairment, especially in the pre-symptomatic stage, is a key step towards enabling disease modification. Cognitive testing that includes pen-and-paper tests has limited sensitivity to detect the onset of the disease before greater impact on memory, language or visuospatial capability occurs. The digital CDT is a fast, sensitive tool that closely correlates with test results from costly brain imaging procedures for screening a population with no apparent symptoms, says Linus Health.

The platform combines cognitive screening tests and remote patient monitoring features to provide a centralized location for detecting early signs of Alzheimer’s, tracking its progression and treating it with lifestyle changes and medical regimens.

Several innovations for Alzheimer’s have seen the light during 2021. One of the most hopeful findings was the deep-learning computer algorithm developed by researchers at Kaunas University of Technology (KTU). They found that this algorithm can accurately detect and differentiate the stages of mild cognitive impairment (MCI) from fMRI scans with over 99 percent accuracy. MCI does not always progress to Alzheimer's disease but it often does, so its early detection may allow those who have it to benefit more from treatment.

Although it is possible to recognize MCI manually in fMRI images, this is a time-consuming task that requires detailed knowledge. As such, it is an ideal candidate for automation using deep learning. Researchers modified a well-known existing algorithm, ResNet 18, to fine-tune it for detecting MCI. After the training process, the researchers tested the algorithm by classifying fMRI scans from 138 individuals. The scans depicted six cognitive stages, starting at healthy control and moving through MCI to Alzheimer’s. This algorithm was 99.99 percent accurate in differentiating between early MCI and Alzheimer’s.

Another development seen this year, was Biogen’s treatment for this disease, just submitted for regulatory approval. While the drug gained FDA’s approval in early June, it was rejected by an EMA panel just on Nov. 17. The drug, called Aducanumab, is an antibody designed to remove amyloid plaque from the brain.

Trials for Aducanumab showed that only one of two large-scale trials significantly slowed progression of the disease, thus the primary chances for the treatment to get approved by the FDA where of 50/50. The EMA’s negative panel vote does not mean that it is the Agency’s final decision but according to comments from Laura Chico, Analyst, Wedbush, to Reuters, it usually is. "Given the existing data and controversy attached to the drug, we see no reason why there would be a divergence (in EMA's decision)," she told Reuters.

Photo by:   Robina Weermeijer on Unsplash

You May Like

Most popular

Newsletter