Onset of Alzheimer’s Disease can be Predicted With Accuracy Using a New Algorithm

Onset of Alzheimer’s disease from brain images can be predicted with more than 99 % accuracy as per a newly developed deep learning-based method – algorithm.

Onset of Alzheimer’s disease can be predicted with almost 100% accuracy as per a newly developed deep learning-based method – algorithm by researchers at the Kaunas University Of Technology, Lithuania.

Alzheimer's disease (AD) is a neurodegenerative disease that leads to gradual memory loss and behavioral changes. It is characterized by the formation of beta-amyloid plaques in the brain tissues, years before the actual symptoms occur.

Alzheimer’s disease - Causes, Symptoms, Diagnosis, Stages, Types, Prevention, Prognosis & Treatment
Alzheimer's disease is a progressive neurodegenerative disease affecting memory and thinking and making the person increasingly dependent on others.

‘Onset of Alzheimer’s disease from brain images can be predicted with more than 99 % accuracy as per a newly developed deep learning-based method – algorithm. This may help notify the medical personnel about the anomalies related to the early onset of Alzheimer’s disease and aid in better treatment.’

It is the most frequent cause of dementia, contributing to up to 70% of dementia cases as per the World Health Organisation (WHO). Globally, the disease affects approximately 24 million people and the number is expected to double every 20 years.

The study team analyzed the functional MRI images from 138 subjects to develop the algorithm using a modification of well-known fine-tuned ResNet 18 (residual neural network). The images were categorized into six different sects: from healthy through the specter of mild cognitive impairment (MCI) to Alzheimer’s disease.

The New Algorithm

Individualized Insights on Alzheimer�s Disease Exhibited by Newly Generated Brain Model
Rate of cognitive decline especially the understanding of Alzheimer’s disease (AD) on an individualized level can now be predicted using a newly developed brain model by scientists.

A total of 51,443 and 27,310 images were selected for training and validation from The Alzheimer’s Disease Neuroimaging Initiative fMRI dataset.

The AI (Artificial Intelligence) method was found to have better performance in terms of accuracy, sensitivity, and specificity than previously developed methods. The MCI features in the given dataset were detected with an accuracy of 99.99%, 99.95%, and 99.95% for early MCI vs. AD, late MCI vs. AD, and MCI vs. early MCI, respectively.

Hallmark Pathology of Alzheimer�s Disease can be Halted by �chaperone� Protein
Plaque build-up in Alzheimer’s disease and various neurodegenerative diseases can be prevented by restoring a “chaperone” protein.

The study thereby affirms that this algorithm could be developed into the software which would help notify the medical personnel about the anomalies related to the early onset of Alzheimer’s disease and aid better treatment.

“Although this was not the first attempt to diagnose the early onset of Alzheimer’s from similar data, our main breakthrough is the accuracy of the algorithm. Obviously, such high numbers are not indicators of true real-life performance, but we’re working with medical institutions to get more data. Technologies can make medicine more accessible and cheaper. Although they will never (or at least not soon) truly replace the medical professional, technologies can encourage seeking timely diagnosis and help”, says Rytis Maskeliūnas, a researcher at the Department of Multimedia Engineering, Faculty of Informatics, Kaunas University of Technology (KTU), Odusami’s Ph.D. supervisor.

Genetics of Alzheimer’s disease
There are numerous genes that have been discovered that are associated with Alzheimer’s disease and indicate increased risk, aiding genetic counseling and better care.

Source-Medindia