AI Predicts Heart Failure In Muscle Inflammation Patients With 80% Accuracy

Israeli researchers have built an artificial intelligence tool that analyzes ECG tests and predicts heart failure with high accuracy weeks before it happens.The new technology is for sufferers of myositismuscle inflammation — which elevates the risk of heart failure. The physician who led the research, Dr. Shahar Shelly of Rambam Healthcare Campus, told The Times of Israel that it is the first AI tool built especially for this population. It analyzes heart patterns that are unique to them, and can bring about earlier detection than is currently possible, he said.

You must be logged in to view this content.

Researchers Build AI That Builds AI

Artificial intelligence is largely a numbers game. When deep neural networks, a form of AI that learns to discern patterns in data, began surpassing traditional algorithms 10 years ago, it was because we finally had enough data and processing power to make full use of them.

Today’s neural networks are even hungrier for data and power. Training them requires carefully tuning the values of millions or even billions of parameters that characterize these networks, representing the strengths of the connections between artificial neurons. The goal is to find nearly ideal values for them, a process known as optimization, but training the networks to reach this point isn’t easy.

Training could take days, weeks or even months,” said Petar Veličković, a staff research scientist at DeepMind in London.

That may soon change. Boris Knyazev of the University of Guelph in Ontario and his colleagues have designed and trained a “hypernetwork” — a kind of overlord of other neural networks — that could speed up the training process. Given a new, untrained deep neural network designed for some task, the hypernetwork predicts the parameters for the new network in fractions of a second, and in theory could make training unnecessary. Because the hypernetwork learns the extremely complex patterns in the designs of deep neural networks, the work may also have deeper theoretical implications.

For now, the hypernetwork performs surprisingly well in certain settings, but there’s still room for it to grow — which is only natural given the magnitude of the problem. If they can solve it, “this will be pretty impactful across the board for machine learning,” said Veličković.

Source: https://www.quantamagazine.org

Walking Patterns Identify Specific Dementia Type

Walking may be a key clinical tool in helping medics accurately identify the specific type of dementia a patient has, pioneering research has revealed.

Gait Lab

For the first time, scientists at Newcastle University have shown that people with Alzheimer’s disease or Lewy body dementia have unique walking patterns that signal subtle differences between the two conditions. The research, published today in Alzheimer’s & Dementia: The Journal of the Alzheimer’s Association, shows that people with Lewy body dementia change their walking steps more – varying step time and length – and are asymmetric when they move, in comparison to those with Alzheimer’s disease. It is a first significant step towards establishing gait as a clinical biomarker for various subtypes of the disease and could lead to improved treatment plans for patients.

The way we walk can reflect changes in thinking and memory that highlight problems in our brain, such as dementia. “Correctly identifying what type of dementia someone has is important for clinicians and researchers as it allows patients to be given the most appropriate treatment for their needs as soon as possible”, says Dr Ríona McArdle, Post-Doctoral Researcher at Newcastle University’s Faculty of Medical Sciences, who led the Alzheimer’s Society-funded research. The results from this study are exciting as they suggest that walking could be a useful tool to add to the diagnostic toolbox for dementia. It is a key development as a more accurate diagnosis means that we know that people are getting the right treatment, care and management for the dementia they have.

Current diagnosis of the two types of dementia is made through identifying different symptoms and, when required, a brain scan. For the study, researchers analysed the walk of 110 people, including 29 older adults whose cognition was intact, 36 with Alzheimer’s disease and 45 with Lewy body dementia. The participants took part in a simple walking test at the Gait Lab of the Clinical Ageing Research Unit, an NIHR-funded research initiative jointly run by Newcastle Hospitals NHS Foundation Trust and Newcastle UniversityParticipants moved along a walkway – a mat with thousands of sensors inside – which captured their footsteps as they walked across it at their normal speed and this revealed their walking patterns.

Source: https://www.ncl.ac.uk/