Machine learning could find an answer to Parkinson's progression

The mystery of how Parkinson’s disease progresses could be cracked thanks to researchers at the Australian National University (ANU) and machine learning.

Deborah Apthorp of the ANU Research School of Psychology has won funding for a study that will track early symptoms with the aim of finding possible indicators of progression, using machine learning. This research has received $138,930 over 5 years from the Perpetual Impact Philanthropy Grant.

As it stands, the type of Parkinson’s a diagnosed patient has or how quickly it will progress is hard to determine. Apthorp noted in an ANU report that some individuals can be fine for quite a while while others can experience a more rapid progression.

Event

Join the world's top medtech executives virtually for the leading event in medtech — The Virtual MedTech Conference by AdvaMed

Expect the same high-quality education, world-class speakers and valuable business development in a virtual format. Experience more of the conference with on demand content and partnering, as well as livestreamed sessions.

"There are different types of Parkinson's that can look similar at the point of onset, but they progress very differently. We are hoping the information we collect will differentiate between these different conditions,” Apthorp said. "Ultimately we'd like doctors to be able to conduct tests that can predict how the disease is likely to progress."

Apthrop’s research will look at brain imaging, eye tracking, visual perception and postural sway altogether.  

"Human posture is an inherently unstable system, so you're constantly making little corrections," Apthorp said in the article. "When you get Parkinson's disease it becomes harder and harder to maintain that upright posture, and you have to think more about it. Eventually as the disease gets further along you start to fall and have trouble walking.”

Apthorp also noted that evidence points to control of eye movement being related to the parts of the brain that are impacted by Parkinson’s. Researchers from the ANU College of Engineering and Computer Science will analyze the data with the project team once they are collected. That is when machine learning will come into play.

"We'll be using machine learning techniques to find patterns in the data that indicate degradation of motor function correlating with Parkinson,” Apthrop said. "The huge quantitative data set available from real time sway measurements will allow us to develop much more precise diagnostic indicators on the disease progression than can be obtained from traditional questionnaires.”

This study will take 5 years to conduct and is set to begin in September. It will be based out of Canberra Hospital where 120 Parkinson’s sufferers and 120 non-sufferers (control group) will take part in it.

Findings could help those like Ken Hood, who was diagnosed with the disease in 1989. Ken Hood noted his shock at how little information was offered on what he was experiencing. His wife, Lesley, shared the same sentiment.

"Having no idea of how Ken's particular Parkinson's might progress, that was very scary," Lesley Hood said. "There was no way of determining what was going to happen. Everything was so unknown that we just had to take things a day at a time."

- here's the ANU news report

Related Articles:
Novartis cancer drug to be tested for Parkinson’s disease
Johns Hopkins researchers reveal novel protein and involvement in Parkinson’s disease
NIH researchers pinpoint potential Gaucher, Parkinson’s candidate

Suggested Articles

Chi-Med has detailed plans to seek approval from the FDA later this year in part on the strength of data from Chinese phase 3 trial.

Takeda tapped Roche’s Foundation Medicine to develop tissue- and blood-based companion diagnostic tests for its portfolio of lung cancer therapies.

The clamor for more transparency from the leading pandemic vaccine contenders has been getting louder.