Posts Tagged Implants

[WEB SITE] Researchers develop new prediction method for epileptic seizures

Epileptic seizures strike with little warning and nearly one third of people living with epilepsy are resistant to treatment that controls these attacks. More than 65 million people worldwide are living with epilepsy.

Now researchers at the University of Sydney have used advanced artificial intelligence and machine learning to develop a generalized method to predict when seizures will strike that will not require surgical implants.

Dr Omid Kavehei from the Faculty of Engineering and IT and the University of Sydney Nano Institute said: “We are on track to develop an affordable, portable and non-surgical device that will give reliable prediction of seizures for people living with treatment-resistant epilepsy.”

In a paper published this month in Neural Networks, Dr Kavehei and his team have proposed a generalized, patient-specific, seizure-prediction method that can alert epilepsy sufferers within 30 minutes of the likelihood of a seizure.

Dr Kavehei said there had been remarkable advances in artificial intelligence as well as micro- and nano-electronics that have allowed the development of such systems.

“Just four years ago, you couldn’t process sophisticated AI through small electronic chips. Now it is completely accessible. In five years, the possibilities will be enormous,” Dr Kavehei said.

The study uses three data sets from Europe and the United States. Using that data, the team has developed a predictive algorithm with sensitivity of up to 81.4 percent and false prediction rate as low as 0.06 an hour.

“While this still leaves some uncertainty, we expect that as our access to seizure data increases, our sensitivity rates will improve,” Dr Kavehei said.

Carol Ireland, chief executive of Epilepsy Action Australia, said: “Living with constant uncertainty significantly contributes to increased anxiety in people with epilepsy and their families, never knowing when the next seizure may occur.

“Even people with well controlled epilepsy have expressed their constant concern, not knowing if or when they will experience a seizure at work, school, traveling or out with friends.

“Any progress toward reliable seizure prediction will significantly impact the quality of life and freedom of choice for people living with epilepsy.”

Dr Kavehei and lead author of the study, Nhan Duy Truong, used deep machine learning and data-mining techniques to develop a dynamic analytical tool that can read a patient’s electroencephalogram, or EEG, data from a wearable cap or other portable device to gather EEG data.

Wearable technology could be attached to an affordable device based on the readily available Raspberry Pi technology that could give a patient a 30-minute warning and percentage likelihood of a seizure.

An alarm would be triggered between 30 and five minutes before a seizure onset, giving patients time to find a safe place, reduce stress or initiate an intervention strategy to prevent or control the seizure.

Dr Kavehei said an advantage of their system is that is unlikely to require regulatory approval, and could easily work with existing implanted systems or medical treatments.

The algorithm that Dr Kavehei and team have developed can generate optimized features for each patient. They do this using what is known as a ‘convolutional neural network’, that is highly attuned to noticing changes in brain activity based on EEG readings.

Other technologies being developed typically require surgical implants or rely on high levels of feature engineering for each patient. Such engineering requires an expert to develop optimized features for each prediction task.

An advantage of Dr Kavehei’s methodology is that the system learns as brain patterns change, requiring minimum feature engineering. This allows for faster and more frequent updates of the information, giving patients maximum benefit from the seizure prediction algorithm.

The next step for the team is to apply the neural networks across much larger data sets of seizure information, improving sensitivity. They are also planning to develop a physical prototype to test the system clinically with partners at the University of Sydney’s Westmead medical campus.

 

via Researchers develop new prediction method for epileptic seizures

, , , , , , ,

Leave a comment

[WEB SITE] Monthly cycles of brain activity linked to seizures in patients with epilepsy

January 8, 2018
UC San Francisco neurologists have discovered monthly cycles of brain activity linked to seizures in patients with epilepsy. The finding, published online January 8 in Nature Communications, suggests it may soon be possible for clinicians to identify when patients are at highest risk for seizures, allowing patients to plan around these brief but potentially dangerous events.

“One of the most disabling aspects of having epilepsy is the seeming randomness of seizures,” said study senior author Vikram Rao, MD, PhD, an assistant professor of neurology at UCSF and member of the UCSF Weill Institute for Neurosciences. “If your neurologist can’t tell you if your next seizure is a minute from now or a year from now, you live your life in a state of constant uncertainty, like walking on eggshells. The exciting thing here is that we may soon be able to empower patients by letting them know when they are at high risk and when they can worry less.”

Epilepsy is a chronic disease characterized by recurrent seizures — brief storms of electrical activity in the brain that can cause convulsions, hallucinations, or loss of consciousness. Epilepsy researchers around the world have been working for decades to identify patterns of electrical activity in the brain that signal an oncoming seizure, but with limited success. In part, Rao says, this is because technology has limited the field to recording brain activity for days to weeks at most, and in artificial inpatient settings.

At UCSF Rao has pioneered the use of an implanted brain stimulation device that can quickly halt seizures by precisely stimulating a patient’s brain as a seizure begins. This device, called the NeuroPace RNS® System, has also made it possible for Rao’s team to record seizure-related brain activity for many months or even years in patients as they go about their normal lives. Using this data, the researchers have begun to show that seizures are less random than they appear. They have identified patterns of electrical discharges in the brain that they term “brain irritability” that are associated with higher likelihood of having a seizure.

Related Stories

  • Adequate intake of choline during pregnancy could provide cognitive benefits for offspring
  • Powerful imaging technique sheds light on how the brain responds to vascular injury
  • Callous-unemotional traits linked to brain structure differences in boys, not girls

The new study, based on recordings from the brains of 37 patients fitted with NeuroPace implants, confirmed previous clinical and research observations of daily cycles in patients’ seizure risk, explaining why many patients tend to experience seizures at the same time of day. But the study also revealed that brain irritability rises and falls in much longer cycles lasting weeks or even months, and that seizures are more likely to occur during the rising phase of these longer cycles, just before the peak. The lengths of these long cycles differ from person to person but are highly stable over many years in individual patients, the researchers found.

The researchers show in the paper that when the highest-risk parts of a patient’s daily and long-term cycles of brain irritability overlap, seizures are nearly seven times more likely to occur than when the two cycles are mismatched.

Rao’s team is now using this data to develop a new approach to forecasting patients’ seizure risk, which could allow patients to avoid potentially dangerous activities such as swimming or driving when their seizure risk is highest, and to potentially take steps (such as additional medication doses) to reduce their seizure risk, similar to how people with asthma know to take extra care to bring their inhalers when pollen levels are high.

“I like to compare it to a weather forecast,” Rao said. “In the past, the field has focused on predicting the exact moment a seizure will occur, which is like predicting when lightning will strike. That’s pretty hard. It may be more useful to be able tell people there is a 5 percent chance of a thunderstorm this week, but a 90 percent chance next week. That kind of information lets you prepare.”

Source:
https://www.ucsf.edu/

via Monthly cycles of brain activity linked to seizures in patients with epilepsy

, , , , , , , , , , , ,

Leave a comment

%d bloggers like this: