Machine learning to help prevent seizures and monitor patients

December 07, 2020

Researchers from Australia’s national science agency, CSIRO, have developed new implantable devices equipped with machine learning to help prevent seizures and monitor patients after brain surgery.

The researchers will now use a $1 million Australian Government grant awarded to Australian company Anatomics to develop a ‘smart helmet’ to monitor brain swelling in stroke and traumatic brain injury patients

Researcher at CSIRO’s data and digital specialist arm, Data61, Dr Umut Guvenc said traumatic brain injuries affect over 69 million people worldwide  , including 700,000 Australians  , with one in three likely to develop chronic epilepsy due to the high frequency of seizures.

“Monitoring brain activity post-surgery is especially critical to a patient’s recovery as seizures can regularly occur, often leading to patients developing epilepsy,” Dr Guvenc said.

“These seizures are often difficult to detect, with current monitoring techniques only able to be used in a hospital using bulky devices for less than 24 hours, providing a brief snapshot of brain activity during that time only.

“This new method can continuously monitor brain activity wirelessly, allowing the patient to be mobile, comfortable and more socially active.” The machine learning in the devices was trained using data from Monash University, and can detect even the smallest seizures before transferring the data securely from the helmet to the healthcare practitioner.

During normal brain activity, the implants stay in standby mode to conserve energy while monitoring brain activity for seizures, and are reactivated when a seizure is detected, sampling the signal at higher resolution.

Senior Research Engineer at Data61, Peter Marendy, said the project aims to use the insights from the helmets to develop a ‘brain machine interface’, enabling clinicians to monitor brain function in real-time.

“Information provided by the implants can be used to inform clinicians about the patient’s brain activity and inform decisions regarding the administering of drugs,” Mr Marendy said.

“The combination of brain swelling, surgery timing and patient outcome data will enable further study on the ideal time to perform a reconstructive cranioplasty to achieve the best patient outcome – research that will ultimately influence future medical decisions.”

Dr Ganesha Thayaparan is R&D Fellow at Anatomics Pty Ltd  . “Anatomics’ ongoing collaboration with CSIRO has produced a number of medical world-firsts, including additively manufactured patient-specific titanium implants,” Dr Thayaparan said.

“The ‘smart helmet’ project builds upon our existing SkullPro technology to develop a remote sensing platform to monitor the injured brain following a decompressive craniectomy.”

The development of these technologies was enabled by CSIRO’s Probing Biosystems Future Science Platform, which provided initial funding to support this cutting-edge research. The work also brought together cross-domain experts from across CSIRO including energy and mineral resources researchers who are developing the micro batteries used in the implants.

For further information and project updates, or to collaborate, please visit Project: Brain Implants.

First published by CSIRO.au

Related stories

Leave a Reply

Your email address will not be published. Required fields are marked *