Mr Ben Goudey, a researcher at Genomics Research Team, Australia, claims that International Business Machine (IBM) learning model has proved capacity to detect early onset of terminal neuro-degenerative diseases — Alzheimer’s disease
He also claimed that the learning model could drastically slow down the progression of Alzheimer’s disease.
In an online publication, Goudey explained that Alzheimer has been diagnosed to be the cause of dementia — a decline in thinking and person’s pattern of behaviour.
“IBM learning model has shown capacity of predicting the severity of the Alzheimer’s disease as well as slow its progression. The company’s Australian arm, IBM Research, Australia, undertook a research and published its findings in journal Scientific Reports. The research could be a breakthrough amid failed clinical trials that have been conducted since 2002 to find a cure or a modifying therapy for this illness. It is thought that the high failure rate of these trials may be because the people enrolled are in the latest stages of the disease,’’ the researcher explained.
IBM official further explained that its machine learning model could also help researchers to find samples with mild cognitive impairment and get-better results.
Citing a previous research, Goudey said: “Examining the concentration of the peptide in an individual’s spinal fluid provides an indication of risk decades before any memory related issues occur. The company says that accessing spinal fluid is highly invasive and is expensive to conduct on large segments of the population. There is a strong effort in the research community to develop a less invasive test, such as a blood test that can yield information about Alzheimer’s disease risk,’’ he said.
According to Goudey, the findings of the research will be presented at the 14th International Conference on Alzheimer’s and Parkinson’s diseases from March 26 to March 31 in Lisbon, Portugal.
“The models we built could one day help clinicians to predict this risk with an accuracy of up to 77 per cent,’’ he claimed.
The paper published by the team shows how the learning model can be used to identify proteins in blood that can predict the concentration of amyloid-beta in spinal fluid, he explained.
“While the test is still in the early phases of research, it could potentially help top improve the selection of individuals for drug trials,’’ he said.