Researchers at Monash University may have developed a world-first artificial intelligence model that predicts the best seizure-control medication for epilepsy patients.
The model, which is still being tested, may spare these individuals from the dangers of taking seizure medications that don’t work or from the confusion of not knowing when their lives will return to normal.
Professor Patrick Kwan, a neurologist and researcher from the Monash Central Clinical School’s Department of Neuroscience is leading an international collaboration that is ‘training’ the deep-learning prediction model (deep learning is a type of machine learning).
Their study is published in the influential JAMA Neurology.
Epilepsy affects 70 million people worldwide. Currently, choosing anti-seizure drugs for a patient is a process of trial and error with clinicians unable to predict which drug a particular patient will respond to, Professor Kwan said.
According to Professor Kwan if the patient doesn’t respond to the first treatment, quite a few will respond to the second or third one, meaning that they might have become seizure-free sooner if the ‘right’ drug was chosen at the outset,”
“But if they get the wrong medication they still have seizures and may also get side-effects from it – they’re not getting the benefit and are getting harm from the drug.” says Kwan
Patients may develop drug-resistant epilepsy that may be treated more quickly with surgical, device, or dietary therapies, without wasting years on therapies that didn’t work. Patients may have a variety of side-effects ranging from allergic reactions to mental issues or even birth defects in their children.
An AI model was created using data from 1798 patients from five hospitals in Australia, Malaysia, China, and the UK, using a Monash Medical AI led by Associate Professor Zongyuan Ge.
The Monash MASSIVE computing cluster was used to train the model.
“We are seeing how the latest deep learning model is bridging itself from the computer-aided diagnosis now to the treatment domain, which is truly exciting,’’ Associate Professor Ge said.
The model’s accuracy in predicting the best medication was “modest”, Professor Kwan said. (It scored 0.65 on a statistical performance measurement known as the AUROC, where 1.0 is most accurate.) “Nonetheless that was more than what we expected – we were happy with that performance because only very basic clinical factors collected in routine clinical care were used to train this base model.”
The model is being improved in both technical and informational aspects to assist with treatment selection in epilepsy. A nationwide multicentre randomised controlled PERSONAL trial (Personalised Selection of Medication for Newly Diagnosed Adult Epilepsy) will test the enhanced model.
Dr Zhibin Chen, Monash neuroscientist and biostatistician, played a pivotal role in the study.
“This is believed to be a world-first model,” Dr Chen said. “It assures the predictability of choosing the optimal treatment for patients with newly diagnosed epilepsy. It will open the gate for personalising the management of epilepsy.”
Dr Haris Hakeem, PhD student and Epilepsy Fellow at The Alfred, was first author while PhD students Wei Feng and Jiun Choong played crucial roles in developing the model, Professor Kwan said.
It is hoped that this research will eventually improve the management and treatment of epilepsy. It is designed to predict responses to treatment, not actual seizures.
At the moment the model is for adults with new onset epilepsy who are going to start their first medication. It has not been tested in children.
This model will form the basis for further models for people with more established epilepsy.
The PERSONAL trial received a $2.46 million NHMRC grant in the latest round of the NHMRC Clinical Trials and Cohort Studies Scheme funding.
