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

Now testing patients and controls in rural and regional NSW

We are now beginning in-person testing of Parkinson’s patients and controls in rural and regional NSW. We have already tested our first Tamworth cohort, and will be testing in Newcastle early next month. Ph.D. student Alycia Messing is heading up the study, and is particularly keen to recruit age-matched controls over 60 for the study. The study involves a non-invasive brain scan using EEG (electroencephalogram), some measures of balance (postural sway), a finger tapping task and some cognitive measures. For the Parkinson’s patients we are also taking some clinical measurements. We’ll be doing this across 18 months at 3 time points, and we’ll come to your town. If you’re keen to participate, please contact Alycia on

National survey recently completed

We have recently completed a national survey aimed at building a better understanding of how people with Parkinson’s and their families are coping with the disease. We considered it particularly important to have representation from people in rural and regional Australia. This was 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. Results will be released soon.

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
Associate Professor in Psychology

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


Adoption of artificial intelligence (AI) by the medical community has long been anticipated, endorsed by a stream of machine learning literature showcasing AI systems that yield extraordinary performance. However, many of these systems are likely over-promising and will under-deliver in practice. One key reason is the community’s failure to acknowledge and address the presence of inflationary effects in the data. These simultaneously inflate evaluation performance and prevent a model from learning the underlying task, thus severely misrepresenting how that model would perform in the real world. This paper investigated the impact of these inflationary effects on healthcare tasks, as well as how these effects can be addressed. Specifically, we defined three inflationary effects that occur in medical data sets and allow models to easily reach small training losses and prevent skillful learning. We investigated two data sets of sustained vowel phonation from participants with and without Parkinson’s disease, and revealed that published models which have achieved high classification performances on these were artificially enhanced due to the inflationary effects. Our experiments showed that removing each inflationary effect corresponded with a decrease in classification accuracy, and that removing all inflationary effects reduced the evaluated performance by up to 30 percent. Additionally, the performance on a more realistic test set increased, suggesting that the removal of these inflationary effects enabled the model to better learn the underlying task and generalize. Source code is available at under the MIT license.

Resting-state electroencephalography (RSEEG) is a method under consideration as a potential biomarker that could support early and accurate diagnosis of Parkinson’s disease (PD). RSEEG data is often contaminated by signals arising from other electrophysiological sources and the environment, necessitating pre-processing of the data prior to applying machine learning methods for classification. Importantly, using differing degrees of pre-processing will lead to different classification results. This study aimed to examine this by evaluating the difference in experimental results when using re-referenced data, data that had undergone filtering and artefact rejection, and data without muscle artefact. The results demonstrated that, using a Random Forest Classifier for feature selection and a Support Vector Machine for disease classification, different levels of pre-processing led to markedly different classification results. In particular, the presence of muscle artefact was associated with inflated classification accuracy, emphasising the importance of its removal as part of pre-processing.

Parkinson’s Disease (PD) is a progressive chronic disorder with a high misdiagnosis rate. Because finger-tapping tasks correlate with its fine-motor symptoms, they could be used to help diagnose and assess PD. We first designed and developed an Android application to perform finger-tapping tasks without trained supervision, which is not always feasible for patients. Then, we conducted a preliminary user evaluation in Australia with six patients clinically diagnosed with PD and sixteen controls without PD. The application could be used in research and healthcare for regular symptom and progression assessment and feedback.

Current tests of disease status in Parkinson’s disease suffer from high variability, limiting their ability to determine disease severity and prognosis. Event-related potentials, in conjunction with machine learning, may provide a more objective assessment. In this study, we will use event-related potentials to develop machine learning models, aiming to provide an objective way to assess disease status and predict disease progression in Parkinson’s disease.

Computer-assisted quantification and analysis of postural sway may support identifying individuals affected by Parkinson’s disease (PD). Balancing, and its associated postural sway, is a complex process that requires the cooperation of several sensory systems in the brain. Unsurprisingly, a neurodegenerative disease can affect such processes, manifesting itself in the postural sway of affected individuals. Different aspects of postural sway can be quantified and represented as features, which can be used to distinguish between patients and controls. Our aim, inspired by a recent systematic literature review, was to experimentally determine whether sampling frequency and visual state had a meaningful impact on the effectiveness of features in distinguishing between the two groups, and whether overall discriminability could be improved using machine learning. We extracted 102 unique features from 78 postural sway recordings and found that the effectiveness (quantified by an effect size and the average area under the receiver operating characteristic curve) with a sampling frequency of 10 Hz was superior to 20, 40, and 100 Hz, though not with high confidence (quantified through Bayesian analysis). We also concluded that effectiveness under the eyes closed condition was higher than the eyes open condition (confirmed through Bayesian analysis), though combining features from both conditions was superior. Finally, we showed that using machine learning to analyse multiple features through feature selection resulted in higher discriminability in almost all cases. The code for these experiments have been released at under the MIT license. When using our code, please cite this paper.

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.