New Machine Learning program shows promise for early Alzheimer's diagnosis

August 15, 2017
PET scan of a human brain with Alzheimer's disease. Credit: public domain

A new machine learning program developed by researchers at Case Western Reserve University appears to outperform other methods for diagnosing Alzheimer's disease before symptoms begin to interfere with every day living, initial testing shows.

More than 5 million Americans may have Alzheimer's , according to estimates, and the numbers are growing as the population ages. The disease is an irreversible, progressive brain disorder that slowly destroys memory and thinking skills. And while there is no cure, several drugs can delay or prevent symptoms from worsening for up to five years or more, according to the National Institute on Aging and published research.

Meanwhile, early diagnosis and treatment—the goal of the new computer based program—is key to allowing those with the disease to remain independent longer.

The computer program integrates a range of Alzheimer's disease indicators, including mild cognitive impairment. In two successive stages, the algorithm selects the most pertinent to predict who has Alzheimer's.

"Many papers compare the healthy to those with the disease, but there's a continuum," said Anant Madabhushi, F. Alex Nason professor II of biomedical engineering at Case Western Reserve. "We deliberately included mild cognitive impairment, which can be a precursor to Alzheimers, but not always."

In a study published in the journal Scientific Reports, Madabhushi, Asha Singanamalli, who recently earned her master's degree and Haibo Wang, a former postdoctoral researcher, tested the algorithm using data from 149 patients collected via the Alzheimer's Disease Neuroimaging Initiative.

The team developed what it calls Cascaded Multi-view Canonical Correlation (CaMCCo) algorithm, which integrates measurements from (MRI) scans, features of the hippocampus, glucose metabolism rates in the brain, proteomics, genomics, mild cognitive impairment and other parameters.

Madabhushi's lab has repeatedly found that integrating dissimilar information is valuable for identifying cancers. This is the first time he and his team have done so for diagnosis and characterization of Alzheimer's disease.

"The algorithm assumes each parameter provides a different view of the disease, as if each were a different set of colored spectacles," Madabhushi said.

The program then assesses the variables in a two-stage cascade. First, the algorithm selects the parameters that best distinguish between someone who's healthy and someone who's not. Second, the selects from the unhealthy variables those that best distinguish who has mild cognitive impairment and who has Alzheimer's disease.

"The remaining views are combined to give the best picture," Madabhushi said.

In predicting which patients in the study had Alzheimer's disease, CaMCCo outperformed individual indicators as well as methods that combine them all without selective assessment. It also was better at predicting who had than other methods that combine multiple indicators.

The researchers continue to validate and fine-tune the approach with data from multiple sites. They also plan to use the software in an observational mode: As a collaborating neurologist compiles tests on patients, the computer would run the data. If CaMCCo proves useful in predicting early Alzheimer's, Madabhushi expects to pursue a clinical trial for prospective validation.

Explore further: Machine learning can predict rate of memory change

Related Stories

Machine learning can predict rate of memory change

July 31, 2017
In new research published today, researchers have created a machine learning algorithm that is able to form two distinct groups of people who have early memory problems known as mild cognitive impairment. The algorithm was ...

Scientists use new data mining strategy to spot those at high Alzheimer's risk

July 28, 2017
The push to develop treatments for Alzheimer's disease has been a promising and disappointing endeavor over the past two decades, yielding a greater understanding of the disease yet still failing to generate successful new ...

Artificial intelligence may aid in Alzheimer's diagnosis

July 6, 2016
Machine learning is a type of artificial intelligence that allows computer programs to learn when exposed to new data without being programmed. Now, researchers in The Netherlands have coupled machine learning methods with ...

Alzheimer's drug prescribed 'off-label' for mild cognitive impairment could pose risk for some

February 24, 2017
Donepezil, a medication that is approved to treat people with Alzheimer's disease, should not be prescribed for people with mild cognitive impairment without a genetic test. UCLA School of Nursing researchers discovered that ...

A step forward searching for an early biomarker of Alzheimer's disease

July 19, 2016
Researchers from Centre for Biomedical Technology (CTB) at Universidad Politécnica de Madrid (UPM) have shown that the abnormal pattern of functional connectivity in patients with mild cognitive impairment can be considered ...

Recommended for you

Personality changes don't precede clinical onset of Alzheimer's, study shows

September 21, 2017
For years, scientists and physicians have been debating whether personality and behavior changes might appear prior to the onset of Alzheimer's disease and related dementias.

Newly ID'd role of major Alzheimer's gene suggests possible therapeutic target

September 20, 2017
Nearly a quarter century ago, a genetic variant known as ApoE4 was identified as a major risk factor for Alzheimer's disease—one that increases a person's chances of developing the neurodegenerative disease by up to 12 ...

Is the Alzheimer's gene the ring leader or the sidekick?

September 15, 2017
The notorious genetic marker of Alzheimer's disease and other forms of dementia, ApoE4, may not be a lone wolf.

Potential noninvasive test for Alzheimer's disease

September 6, 2017
In the largest and most conclusive study of its kind, researchers have analysed blood samples to create a novel and non-invasive way of helping to diagnose Alzheimer's disease and distinguishing between different types of ...

Researchers unlock the molecular origins of Alzheimer's disease

September 6, 2017
A "twist of fate" that is minuscule even on the molecular level may cause the development of Alzheimer's disease, VCU researchers have found.

Is dementia declining among older Americans?

September 5, 2017
(HealthDay)—Here's some good news for America's seniors: The rates of Alzheimer's and other forms of dementia have dropped significantly over the last decade or so, a new study shows.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.