Study trains AI to predict optimal antiepileptic drugs for new epilepsy patients

An international study led by Monash University has done what could be the world’s first demonstration of an AI model that can predict the optimal antiepileptic drug for patients with newly diagnosed epilepsy.


The team trained a deep learning prediction model using clinical information from approximately 1,800 patients at five healthcare centers in Australia, Malaysia, China and the United Kingdom. The model was designed by Monash Medical AI Group and trained using Monash’s MASSIVE computing facility.

Word detection researchpublished in the journal JAMA Neurology, found that the AI ​​model had a “modest” 65% accuracy in predicting the best antiepileptic drug.

The team is still refining the model using more complex information. The enhanced prediction model will then be tested in a nationwide multi-site randomized controlled trial called PERSONAL (Personalized Drug Choice for Newly Diagnosed Adult Epilepsy). ). According to Monash, the said trial, which has received A$2.46 million ($1.7 million) funding from the Australian government’s National Health and Medical Research Council, is designed to predict responses to epilepsy treatment, but not actual seizures.


About 70 million people worldwide have epilepsy. Patrick Kwan, professor and neuroscientist from the Department of Neuroscience at Monash Central Clinical School, who led the international study, said that so far, there has been a lot of guesswork and testing of the scientists. doctors about the type of anticonvulsant that their patient will respond to.

He added that this trial-and-error process can do more harm to patients than good. Side effects can range from allergies to psychiatric problems, or in the case of women, birth defects in their babies.

Dr Zhibin Chen, neuroscientist and biostatistician from Monash, said their AI model “will open the door to personalized epilepsy management”.

Currently, the prediction model is for adults with new-onset epilepsy who are about to start taking medication. Monash said the model will serve as the basis for future models for people with more established epilepsy.


Research in India has produced the novel algorithms can identify the source of epileptic seizures using the patient’s EEG data. Developed by researchers from the Indian Institute of Technology – Delhi, head harmonic-based array processing algorithms can determine the exact coordinates of a seizure within minutes. These algorithms were validated in a study recently published in the journal Nature Scientific Reports.

Wearable technology is the latest in seizure detection, such as Epitel’s REMI system, which includes a wireless EEG sensor worn below the hairline and software for providers to review data. and monitor seizures. Earlier this year, the US-based company scored $12.5 million in Series A funding to commercialize their products.

Source link


News5h: Update the world's latest breaking news online of the day, breaking news, politics, society today, international mainstream news .Updated news 24/7: Entertainment, the World everyday world. Hot news, images, video clips that are updated quickly and reliably

Related Articles

Back to top button