The system, which is based on machine learning for EEG signal analysis, can predict epileptic seizures about an hour before they occur. * NeuroHelp, a newly established start-up company licensed to develop and commercialize technology, is an accelerator portfolio company Oasis, Of center Entrepreneurship 360 Of Ben-Gurion University
Researchers at Ben-Gurion University of the Negev have developed an innovative and first-of-its-kind device for detecting and predicting epileptic seizures using machine learning algorithms. The wearable device can produce an early warning of an oncoming attack that will be sent to the cell phone about an hour before the onset of the attack. A license for the development and commercialization of the system is given to NeuroHelp, a company recently established by BGN Technologies, Ben-Gurion University’s technology commercialization company in collaboration with Dr. Oren Shrikki from the Department of Cognitive and Brain Sciences at Ben-Gurion University and the scientific founder of NeuroHelp.
Epilepsy is a neuropathic disease with extensive effects and varying degrees of severity. About 30% of patients do not respond optimally to medication and they live in constant fear of seizures. For these patients, an effective seizure prediction device can significantly improve their quality of life and allow them to avoid injuries due to the seizures.
Existing devices that warn of seizures today can detect a seizure in real time but are unable to provide an early warning of an impending seizure. The innovative device for predicting and detecting seizures is based on a unique combination of monitoring brain activity with the help of EEG and machine learning algorithms.
Dr. Oren Shrikki said, “Epileptic seizures expose epileptic patients to a variety of preventable risks, including falls, burns and other injuries. Unfortunately, there are currently no seizure prediction devices that can alert patients to an impending seizure and allow them to prepare for it. “Due to imminent seizures, up to about an hour before they occur. Because we have also shown that our algorithm supports a significant reduction in the number of EEG electrodes required, the device we are developing will be both accurate and user-friendly. We are currently developing a prototype ready for evaluation in human clinical trials later this year.”
The system combines an EEG device with advanced software that minimizes the number of EEG electrodes needed and provides information on the optimal position of the electrodes on the scalp. Sophisticated algorithms filter out background noises unrelated to brain activity, extract informative measures of brain activity and distinguish between pre-seizure brain activity and non-pre-seizure brain activity.
Dr. Hadar Ron, Chairman of the Board of Directors of NeuroHelp, Noted, “Epilepsy that does not respond optimally to medication characterizes up to 30% of epilepsy cases, and therefore an accurate and easy-to-use device for predicting seizures is a real medical need that has no answer. Or falls.Our device is unique in that it can predict seizures and allow patients and their treatment staff to take precautionary measures to prevent injuries.It is also the only non-invasive device, which is based on brain activity and not on muscle movements or heart rate.We are confident that it will be a significant management device Epilepsy resistant to drug treatment. “
Josh Peleg, CEOTechnologies BGN, Ben-Gurion University’s Technology Commercialization Company, added, “NeuroHelp, a subsidiary of BGN Technologies, was recently founded as part of Ben-Gurion University’s Oasis Accelerator to continue to develop and market their innovative solution for the benefit of people with epilepsy. “An important recognition of the extraordinary potential of this technology, which is based on a unique combination of brain research and artificial intelligence developed in Dr. Shrikki’s laboratory.”
The new algorithm was developed and tested on EEG data from a large database of people with epilepsy whose brain activity was monitored for several days before surgery. Patients’ data were divided into short sections of pre-seizure activity or during seizure. Several machine learning algorithms with varying levels of complexity were trained on a database initially assigned to training (80% of the total EEG data in the database), and then their ability to predict an attack was tested on the remaining EEG data (20% of the total EEG data in the database). The efficiency of the various algorithms was also examined depending on the number of EEG electrodes. The algorithm with the best predictive power reached an accuracy of 97%, and its predictive power was almost unaffected (95% accuracy) even when it relied on a relatively small number of electrodes.
Epilepsy is a non-communicable chronic brain disease that affects about 65 million people worldwide. It is characterized by recurrent seizures, which are brief events of involuntary movements that may involve one area of the body or the entire body, often accompanied by loss of consciousness and loss of control of the sphincters. The seizures are the result of increased electrical activity of a group of brain cells. Different areas of the brain can be sites for this increased activity. Seizures can range from a short conscious detachment or a small muscle spasm to severe and prolonged spasms. The frequency of seizures also varies, from less than one per year to the number of seizures per day.
More on the subject on the Yadan website:
Source link by https://www.hayadan.org.il/%D7%97%D7%95%D7%A7%D7%A8%D7%99%D7%9D-%D7%91%D7%90%D7%95%D7%A0%D7%99%D7%91%D7%A8%D7%A1%D7%99%D7%98%D7%AA-%D7%91%D7%9F-%D7%92%D7%95%D7%A8%D7%99%D7%95%D7%9F-%D7%A4%D7%99%D7%AA%D7%97%D7%95-%D7%9E%D7%A2
*The article has been translated based on the content of Source link by https://www.hayadan.org.il/%D7%97%D7%95%D7%A7%D7%A8%D7%99%D7%9D-%D7%91%D7%90%D7%95%D7%A0%D7%99%D7%91%D7%A8%D7%A1%D7%99%D7%98%D7%AA-%D7%91%D7%9F-%D7%92%D7%95%D7%A8%D7%99%D7%95%D7%9F-%D7%A4%D7%99%D7%AA%D7%97%D7%95-%D7%9E%D7%A2
. If there is any problem regarding the content, copyright, please leave a report below the article. We will try to process as quickly as possible to protect the rights of the author. Thank you very much!
*We just want readers to access information more quickly and easily with other multilingual content, instead of information only available in a certain language.
*We always respect the copyright of the content of the author and always include the original link of the source article.If the author disagrees, just leave the report below the article, the article will be edited or deleted at the request of the author. Thanks very much! Best regards!