IBM machine learning tech can aid the early detection of Alzheimer’s

The smart technology analyses blood samples rather than rely on the intrusive extraction of spinal fluid


IBM researchers have used the power of machine learning to come up with a new way to detect the signs of early Alzheimer's disease through the analysis of blood.

Through the use of IBM's artificial intelligence tech, the researchers were able to apply smart computing to the analysis of proteins in blood, which in turn allowed clinicians to predict the concentration of amyloid-beta, a peptide that's a biological marker of Alzheimer's, in spinal fluid.

From the detection of the peptide, the disease can be spotted even earlier than conducting a brain scan, thereby giving doctors more time to care for a patient with Alzheimer's and potentially slow down the onset of the neurological disease.

Previous early detection of Alzheimer's would involve the extraction and examination of spinal fluid for the concentration of amyloid-beta. But this is an invasive process for a patient, as well as an expensive process.

Advertisement - Article continues below

However, the analysis of blood has thus far proven to be up to 77% accurate and is a lot less invasive than extracting spinal fluid.

While the AI testing is still in its infancy, it does pave the way for clinicians and researchers to find new ways to detect Alzheimer's disease earlier, without needing to put a patient through intrusive tests.

"It could potentially help improve the selection of individuals for drug trials: individuals with mild cognitive impairment who were predicted to have an abnormal concentration of amyloid in their spinal fluid were found to be 2.5 times more likely to develop Alzheimer's disease," said Ben Goudey, staff researcher at IBM Research's genomics research team.

A cure for Alzheimer's currently remains out of reach of researchers and clinicians, even with the power of Ai technology supporting them. But advancements in machine learning techniques ad technology are at least paving the way for faster and improved treatments of such complex diseases.

Featured Resources

The essential guide to cloud-based backup and disaster recovery

Support business continuity by building a holistic emergency plan

Download now

Trends in modern data protection

A comprehensive view of the data protection landscape

Download now

How do vulnerabilities get into software?

90% of security incidents result from exploits against defects in software

Download now

Delivering the future of work - now

The CIO’s guide to building the unified digital workspace for today’s hybrid and multi-cloud strategies.

Download now



Toyota, NVIDIA partner on self-driving cars

20 Mar 2019

Most Popular

Microsoft Azure

Microsoft, not Amazon, is going to win the cloud wars

30 Nov 2019
Amazon Web Services (AWS)

What to expect from AWS Re:Invent 2019

29 Nov 2019

Raspberry Pi 4 owners complain of broken Wi-Fi when using HDMI

29 Nov 2019
Google Android

Samsung Galaxy A90 5G review: Simply the best value 5G phone

22 Nov 2019