Front and side views of a man portrayed to be suffering from Parkinson’s disease.

Parkinson's disease

Front and side views of a man portrayed to be suffering from Parkinson’s disease.

Parkinson's disease

National survey recently launched

We have recently launched a new national survey aimed at build a better understanding of how people with Parkinson’s and their families are coping with the disease. It is particularly important that we have representation from people in rural and regional Australia. This will be the first Australia-wide survey specifically looking at quality of life for people with Parkinson’s in rural and regional Australia compared to those in metropolitan areas. The survey can be found here:

UNE Parkinson’s Disease Survey

Report for UNE Media by Amanda Burdon

Researchers at UNE’s School of Psychology have recently secured funding from the Perpetual Impact Philanthropy Foundation to use mobile technology and machine learning to help solve the mystery of how to determine the progression of Parkinson’s disease. This study extends a previous study (also headed by Dr. Deborah Apthorp while she was at the Australian National University, and also funded by Perpetual), to extend its reach to rural and regional NSW. Crucially, the team will continue to collaborate with colleagues at the Australian National University, tapping the expertise of clinicians and data scientists at The Canberra Hospital and ANU’s Research School of Computer Science.

Currently, when someone is diagnosed with Parkinson’s disease it is difficult to determine what type of Parkinson’s they have or how quickly the condition will progress. This project aims to tracks a range of early symptoms to determine if any can be used as an indicator of progression.

“The issue with Parkinson’s disease is that some people can do well for quite a long time, while others within five or 10 years will be constrained to a nursing home,” Dr Apthorp said.

“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.

“Ultimately we’d like doctors and other primary health professionals to be able to conduct simple, accurate tests that can help predict how the disease is likely to progress.”

The research is using brain imaging EEG techniques, as well as eye tracking, visual perception, simple finger tapping tests, and postural sway, in addition to more traditional clinical measures.

“Human posture is an inherently unstable system, so you’re constantly making small corrections,” Dr Apthorp said. “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 might start to fall or have difficulty walking.

“There is also some evidence that speed of eye movement is related to parts of the brain that are impacted by Parkinson’s, so we plan to look at all these measures together”

This funding will enable the researchers to equip a mobile research lab custom-built into a van, with EEG, eye tracking equipment, a force plate for measuring balance, and the option to add other technology as it becomes available. The van will be equipped with solar panels to power the instruments, and lined with light-limiting curtains to provide a consistent visual environment anywhere it can be parked.

Initially, the team aims to extend the work from work previously funded by Perpetual at ANU, extending research on machine learning in Parkinson’s disease across remote and rural areas of NSW and southern QLD, based at the University of New England. The overall goal is to develop technology for remote assessment of symptoms associated with neurological disorders like Parkinson’s disease. However, this facility will also be extended to research on Multiple Sclerosis and Diabetes via Dr. Apthorp’s links with ANU’s winning 2017 ANU Grand Challenge team, “Our Health In Our Hands”.

There is a stark lack of accessibility to specialised medical care in remote and rural regions of Australia. For instance, patients in the New England region do not have access to a specialist neurologist without travelling several hours. Since Parkinson’s patients struggle with mobility, they often rely on public transport, which is also limited in these regions. This project offers the possibility that inexpensive technologies such as balance plates (or even mobile phones), combined with other forms of non-invasive, simple data, could offer sufficient information for individuals to track the state of their health, disease progression and response to medication in the comfort of their own homes, or in a simple rural clinic setting. This team have advanced expertise in signal processing and data analysis to develop these new measures, and now we seek the ability to reach patients and empower them to participate in research that can shape their future.

Deborah Apthorp
Senior Lecturer in Psychology

My research interests include visual perception, Parkinson’s disease, postural sway, and EEG.


We measured postural sway in individuals diagnosed with Parkinson’s disease and age-matched controls. Individuals with Parkinson’s swayed more, as expected, especially when their eyes were closed. In the people with Parkinson’s, sway correlated strongly with cognitive measures, as well as with measures of quality of life and clinical status.

Background: Postural sway may be useful as an objective measure of Parkinson’s disease (PD). Existing studies have analyzed many different features of sway using different experimental paradigms. We aimed to determine what features have been used to measure sway and then to assess which feature(s) best differentiate PD patients from controls. We also aimed to determine whether any refinements might improve discriminative power and so assist in standardizing experimental conditions and analysis of data.

Methods: In this systematic review of the literature, effect size (ES) was calculated for every feature reported by each article and then collapsed across articles where appropriate. The influence of clinical medication status, visual state, and sampling rate on ES was also assessed. Results: Four hundred and forty‐three papers were retrieved. 25 contained enough information for further analysis. The most commonly used features were not the most effective (e.g., PathLength, used 14 times, had ES of 0.47, while TotalEnergy, used only once, had ES of 1.78). Increased sampling rate was associated with increased ES (PathLength ES increased to 1.12 at 100 Hz from 0.40 at 10 Hz). Measurement during “OFF” clinical status was associated with increased ES (PathLength ES was 0.83 OFF compared to 0.21 ON). Conclusions: This review identified promising features for analysis of postural sway in PD, recommending a sampling rate of 100 Hz and studying patients when OFF to maximize ES. ES complements statistical significance as it is clinically relevant and is easily compared across experiments. We suggest that machine learning is a promising tool for the future analysis of postural sway in PD.

Background: Parkinson disease (PD) is a common neurodegenerative disorder that affects between 7 and 10 million people worldwide. No objective test for PD currently exists, and studies suggest misdiagnosis rates of up to 34%. Machine learning (ML) presents an opportunity to improve diagnosis; however, the size and nature of data sets make it difficult to generalize the performance of ML models to real-world applications. Objective: This study aims to consolidate prior work and introduce new techniques in feature engineering and ML for diagnosis based on vowel phonation. Additional features and ML techniques were introduced, showing major performance improvements on the large mPower vocal phonation data set. Methods: We used 1600 randomly selected /aa/ phonation samples from the entire data set to derive rules for filtering out faulty samples from the data set. The application of these rules, along with a joint age-gender balancing filter, results in a data set of 511 PD patients and 511 controls. We calculated features on a 1.5-second window of audio, beginning at the 1-second mark, for a support vector machine. This was evaluated with 10-fold cross-validation (CV), with stratification for balancing the number of patients and controls for each CV fold. Results: We showed that the features used in prior literature do not perform well when extrapolated to the much larger mPower data set. Owing to the natural variation in speech, the separation of patients and controls is not as simple as previously believed. We presented significant performance improvements using additional novel features (with 88.6% certainty, derived from a Bayesian correlated t test) in separating patients and controls, with accuracy exceeding 58%. Conclusions: The results are promising, showing the potential for ML in detecting symptoms imperceptible to a neurologist.