IBM machine learning could help with early Alzheimer’s detection

Alzheimer’s

IBM has introduced machine learning (ML) to the medical diagnostic fields in the hope that it could one day help clinicians predict the risk of Alzheimer’s disease long before it gets detected.

On Monday, the tech company said ML and artificial intelligence (AL) can be exploited to develop less invasive and expensive tests for the disease.

The paper documenting the research, conducted by IBMs Australian team, has been published in natures.com Scientific Reports on Monday (March.11th).

Alzheimer’s disease

Alzheimer’s remains an incurable, fatal disease suffered by millions of people from around the world, and can only be treated by palliative means.

Alzheimer’s is a progressive disease, with symptoms including gradual degradation of memory, confusion, and dementia, which can make many everyday tasks increasingly problematic.

According to the report, today’s methods for diagnosing the early stages of Alzheimer’s are not only costly, but extremely invasive. These include finding a particular biological marker found in the spinal fluid, which may require a lumbar puncture and can potentially lead to bleeding inside the brain afterward.

While there are no methods to treat the disease, developing new ways to detect the disease in its earlier stages, without the need for invasive tests, could prove to be a catalyst for a new wave of clinical tests which do not rely on those involved in the later stages of the disease, in which brain tissue damage is already underway.

According to IBM, ML may help bridge the gap between early detection and clinical tests.

Amyloid-beta

The use of such technology hinges upon amyloid-beta, a peptide that changes long before any memory-related issues begin to occur.

IBM claims that they used machine learning to identify a set of specific proteins in the blood which can predict the concentration of amyloid-beta in spinal fluid.

“The models we built could one-day help clinicians to predict this risk with an accuracy of up to 77%. While the test is still in the early phases of research, 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,” Ben Goudey, staff researcher, genomics research team, IBM research, wrote in a blog post.

IBM also claims that amid the wide range of other proposed blood tests for Alzheimer’s disease that are currently being developed, this is the first study to use machine learning to identify sets of proteins in the blood that are predictive of a biomarker in spinal fluid.

The findings of the research will be presented at the 14th International Conference on Alzheimer’s and Parkinson’s Diseases in Lisbon at the end of the month.

“At IBM Research, our mission is to use AI and technology to understand how to help clinicians better detect and ultimately prevent these diseases in their early stages. Whether that’s through retinal imaging, blood biomarkers or minor changes in speech, we envision a future in which health professionals have a wide array of easily accessible data available to more clearly identify and track the onset and acceleration of these conditions,” Goudey added.

Related Posts

Menu