New Algorithm Predicts Alzheimer’s with 99% accuracy

Researchers from Kaunas universities in Lithuania developed a deep learning-based method that can predict the possible onset of Alzheimer’s disease from brain images with an accuracy of over 99 per cent. The method was developed while analysing functional MRI images obtained from 138 subjects and performed better in terms of accuracy, sensitivity and specificity than previously developed methods.

According to World Health Organisation, Alzheimer’s disease is the most frequent cause of dementia, contributing to up to 70 per cent of dementia cases. Worldwide, approximately 24 million people are affected, and this number 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.

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. This was one of the most important issues for choosing a topic for Modupe Odusami, a PhD student from Nigeria”, says Rytis Maskeliūnas, a researcher at the Department of Multimedia Engineering, Faculty of Informatics, Kaunas University of Technology (KTU), Odusami’s PhD supervisor. One of the possible Alzheimer’s first signs is mild cognitive impairment (MCI), which is the stage between the expected cognitive decline of normal ageing and dementia. Based on the previous research, functional magnetic resonance imaging (fMRI) can be used to identify the regions in the brain which can be associated with the onset of Alzheimer’s disease, according to Maskeliūnas. The earliest stages of MCI often have almost no clear symptoms, but in quite a few cases can be detected by neuroimaging.

However, although theoretically possible, manual analysing of fMRI images attempting to identify the changes associated with Alzheimer’s not only requires specific knowledge but is also time-consuming – application of Deep learning and other AI methods can speed this up by a significant time margin. Finding MCI features does not necessarily mean the presence of illness, as it can also be a symptom of other related diseases, but it is more of an indicator and possible helper to steer toward an evaluation by a medical professional.

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. 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”, says Maskeliūnas, who supervised the team working on the model.


Hair Loss Pre­ven­ted By Reg­u­lat­ing Stem Cell Meta­bol­ism

An international research group headed by Associate Professor Sara Wickström at the University of Helsinki has identified a mechanism that is likely to prevent hair lossHair follicle stem cells, which promote hair growth, can prolong their life by switching their metabolic state. In experiments conducted with mice, a research group active in Helsinki and Cologne, Germany, has demonstrated that a protein called Rictor holds a key role in the process. Ultraviolet radiation and other environmental factors damage our skin and other tissues every day, with the body continuously removing and renewing the damaged tissue. On average, humans shed daily 500 million cells and a quantity of hairs weighing a total of 1.5 grams. The dead material is replaced by specialised stem cells that promote tissue growth. Tissue function is dependent on the activity and health of these stem cells, as impaired activity results in the ageing of the tissues.

Hair follicle stem cells, which promote hair growth, can prolong their life by switching their metabolic state.

Although the critical role of stem cells in ageing is established, little is known about the mechanisms that regulate the long-term maintenance of these important cells. The hair follicle with its well understood functions and clearly identifiable stem cells was a perfect model system to study this important question,” says Sara Wickström.

At the end of hair folliclesregenerative cycle, the moment a new hair is created, stem cells return to their specific location and resume a quiescent state. The key finding in the new study is that this return to the stem cell state requires a change in the cells’ metabolic state. They switch from glutamine-based metabolism and cellular respiration to glycolysis,

a shift triggered by signalling induced by a protein called Rictor, in response to the low oxygen concentration in the tissue. Correspondingly, the present study demonstrated that the absence of the Rictor protein impaired the reversibility of the stem cells, initiating a slow exhaustion of the stem cells and hair loss caused by ageing.

The research group created a genetic mouse model to study the function of the Rictor protein, observing that hair follicle regeneration and cycle were significantly delayed in mice lacking the protein. Ageing mice suffering from Rictor deficiency showed a gradual decrease in their stem cell, resulting in loss of hair.

The study was published in the Cell Metabolism journal.


Blood Iron Levels Are Key To Slowing Ageing

Genes that could help explain why some people age at different rates to others have been identified by scientists. The international study using genetic data from more than a million people suggests that maintaining healthy levels of iron in the blood could be a key to ageing better and living longer. The findings could accelerate the development of drugs to reduce age-related diseases, extend healthy years of life and increase the chances of living to old age free of disease, the researchers say.

Scientists from the University of Edinburgh and the Max Planck Institute for Biology of Ageing in Germany focused on three measures linked to biological ageinglifespan, years of life lived free of disease (healthspan), and being extremely long–lived (longevity). Biological ageing – the rate at which our bodies decline over time – varies between people and drives the world’s most fatal diseases, including heart disease, dementia and cancers. The researchers pooled information from three public datasets to enable an analysis in unprecedented detail. The combined dataset was equivalent to studying 1.75 million lifespans or more than 60,000 extremely long-lived people. The team pinpointed ten regions of the genome linked to long lifespan, healthspan and longevity. They also found that gene sets linked to iron were overrepresented in their analysis of all three measures of ageing. The researchers confirmed this using a statistical method – known as Mendelian randomisation – that suggested that genes involved in metabolising iron in the blood are partly responsible for a healthy long life.

Blood iron is affected by diet and abnormally high or low levels are linked to age-related conditions such as Parkinson’s disease, liver disease and a decline in the body’s ability to fight infection in older age. The researchers say that designing a drug that could mimic the influence of genetic variation on iron metabolism could be a future step to overcome some of the effects of ageing, but caution that more work is required.

Anonymised datasets linking genetic variation to healthspan, lifespan, and longevity were downloaded from the publicly available Zenodo, Edinburgh DataShare and Longevity Genomics servers.

We are very excited by these findings as they strongly suggest that high levels of iron in the blood reduces our healthy years of life, and keeping these levels in check could prevent age-related damage. We speculate that our findings on iron metabolism might also start to explain why very high levels of iron-rich red meat in the diet has been linked to age-related conditions such as heart disease”, said Dr Paul Timmers from the Usher Institute.

The study was funded by the Medical Research Council and is published in the journal Nature Communications.