Kaunas University researchers invent method to predict Alzheimer’s with 99% accuracy

In a major breakthrough in the field of medical science, researchers have developed a deep learning-based method that can predict the possible onset of Alzheimer's disease. According to the researchers of the Kaunas University of Technology, Lithuania, using the latest developed method, the age-related ailment can be predicted with an accuracy of over 99%. The findings of the research were published in the journal 'Diagnostics'.

As per the researchers, they had analysed functional Magnetic resonance imaging (MRI) obtained from 138 subjects. They found the new technique performing better in terms of accuracy, sensitivity and specificity than previously developed methods.

"Medical professionals all over the world attempt to raise awareness of an early Alzheimer's diagnosis, which provides the affected with a better chance of benefiting from treatment," said Rytis Maskeliunas, a researcher at the Department of Multimedia Engineering, Faculty of Informatics, Kaunas University of Technology (KTU), Odusami's PhD supervisor.

Approximately 24 million people are affected by Alzheimer's disease worldwide

According to the reports of the World Health Organisation (WHO), approximately 24 million people are affected by Alzheimer's disease worldwide, and this figure is expected to double every 20 years. Owing to societal ageing, the disease will become a costly public health burden in the years to come.

According to the researchers, the symptoms of the deadly disease include mild cognitive impairment (MCI), which have almost no clear symptoms in the early stages. However, it can be detected in a few cases by neuroimaging, said the researchers. Further, the scientists added that the MCI features sometimes failed to identify the exact disease as it can also be a symptom of other related diseases.

Scientists warn medical professionals to rely fully on machine algorithm

"Modern signal processing allows delegating the image processing to the machine, which can complete it faster and accurately enough. Of course, we don't dare to suggest that a medical professional should ever rely on any algorithm one-hundred-per cent," said Maskeliunas, who supervised the team working on the model.

"Think of a machine as a robot capable of doing the most tedious task of sorting the data and searching for features. In this scenario, after the computer algorithm selects potentially affected cases, the specialist can look into them more closely, and at the end, everybody benefits as the diagnosis and the treatment reaches the patient much faster," added Maskeliunas.

What is Alzheimer?

Alzheimer’s disease is an age-related brain disorder that develops over many years. Toxic changes in the brain slowly destroy memory and thinking skills. Symptoms most often first appear when people are in their mid-60s. The disorder gets worse over time and eventually leads to a severe loss of mental function.

According to the US National Institutes of Health, they had found that PET scans of the brain and lab tests of spinal fluid can reveal disease-related changes or pathology twenty years before the onset of symptoms. The research, which was published last year, however, said that PET imaging is expensive and involves radioactive agents, whereas spinal fluid tests are invasive, complex, and time-consuming.

The researchers revealed that the disorder is not reversible and said that early diagnosis would enable the testing of novel drugs and other treatment approaches. Since then, researchers have been looking for simpler, more cost-effective tests.

(With inputs from ANI)

(Image Credit: ANI)