Monash University researchers speed up epilepsy diagnosis with machine learning

The technology has been designed to automatically detect abnormal activities in electrical recordings.

Monash University researchers speed up epilepsy diagnosis with machine learning

A new study by Monash University, together with Alfred Health and The Royal Melbourne Hospital, has uncovered how machine learning technology could be used to automate epilepsy diagnosis.

As part of the study, Monash University researchers applied over 400 electroencephalogram (EEG) recordings of patients with and without epilepsy from Alfred Health and The Royal Melbourne hospital to a machine learning model. Training the model with the various datasets enabled it to automatically detect signs of epilepsy -- or abnormal activities known as "spikes" in EEG recordings.

"The objective of the first stage is to evaluate existing patterns involved in the detection of abnormal electrical recordings among neurons in the brain, called epileptiform activity. These abnormalities are often sharp spikes which stand out from the rhythmic patterns of a patient's EEG scan," explained Levin Kuhlmann, Monash University senior lecturer at the Faculty of IT Department of Data Science and AI.

Read also: AI and machine learning facilitate pioneering research on Parkinson's (TechRepublic)

Doug Nhu, fellow project researcher and PhD candidate from the faculty said applying machine learning to the process has the potential to free up the time of medical professionals, as the current process to diagnose epilepsy is often a lengthy one.

"Being able to apply a machine learning model across various datasets demonstrates our ability to create an algorithm that is more reliable, adaptive, and intelligent than existing models, making our model more useful when applied in real-world scenarios such as diagnosing patients in a clinic," he said.

In addition to diagnosing epilepsy patients, machine learning technology has the potential to be used as a training tool for graduate neurologists, who can use the technology as a baseline to compare against epilepsy patient records, the university said.

"Our plans for this research will be to continue to improve the current models and further train it against additional datasets from other hospitals," said Patrick Kwan from the Faculty of Medicine's Department of Neuroscience at Monash University.

"We aim to develop an accurate algorithm which will be reliable across multiple hospital settings and usable in the early stages of epilepsy diagnosis, from both routine and sleep-deprived EEG recordings."

According to Kuhlmann, the next stage of the project will see the machine learning model focus on detecting novel seizures and prediction methods. 

Related Coverage

Monash University takes game-like approach to capsule endoscopy

The university has also teamed up with other partners to create an AI system to help teachers maximise student engagement in classrooms.

Monash University and RMIT develop AI and AR device to read emotional cues

Designed to augment emotional communication beyond traditional settings.

IBM, Monash and Southampton Uni develop mind-reading ebike to save live

The bike can read a rider's brain activity to detect if they are in danger.

Monash University researchers use AI technology to examine hospital readmissions

In hope that it will relieve some pressure off the healthcare system.

Monash, Swinburne, and RMIT universities use optical chip to achieve 44Tbps data speed

Claimed as the fastest internet speed that has been tested and recorded in the world.