Parkinson’s Disease (PD) is a neurodegenerative movement disease affecting over 6 million people worldwide. Current diagnosis is based on clinical and observational criteria only, resulting in a high misdiagnosis rate. Approximately 75% of people with PD have hand tremor, which can precede clinical diagnosis by up to 6 years. Previous studies have shown that early PD can be accurately detected from keystroke features while typing, and this study investigated whether tremor can be detected as well. Typing data from 76 subjects, with and without PD, including 27 with PD and 15 with tremor, was analysed and showed that hand tremor in PD can be detected from keystroke features. This novel technique has not been used before and was able to achieve an overall sensitivity of 67% and a specificity of 80% and was also able to differentiate PD tremor from essential tremor. This means that the diagnosis of early PD through typing can achieve the clinical requirement of at least two cardinal fe...

Parkinson’s Disease (PD) is a progressive neurodegenerative movement disease affecting 2% of people at the age of 65 and is the second most commonly occurring neurodegenerative disease in the elderly, with an estimated 80,000 sufferers in Australia and over 6 million worldwide. The loss of dopamine-producing neurons in PD results in a range of both motor and non-motor symptoms, but a patient can have the disease for 5 to 10 years before it is diagnosed, by which time 70% of the neurons in the affected part of the brain (the substantia nigra) may have already been lost.
As the current diagnosis of PD is through observation only, in a clinical setting it is commonly misdiagnosed or missed completely – primary care doctors have a correct diagnosis of just 53% and only movement disorder specialists achieve a correct diagnosis of 75% or higher. Because the most severe symptoms of PD occur in the advanced stages of the disease, strategies aimed at early detection and treatment will have the most benefit.
The problem which was addressed in this research was the need for easier, objective, more accurate and earlier diagnoses of PD, and it investigated whether utilising human-computer interaction (HCI) for the detection and classification of PD based on motor features of the disease could achieve that. In order to be effective, such a technique would need to be significantly more accurate than current non-specialist clinician diagnoses; at least as accurate as any existing tests; be able to detect PD in its early stages where there are just mild symptoms present; not be invasive or require specialised equipment; and be able to be used as the basis for development of both a screening test for PD and for ongoing monitoring of disease status using an e-health platform.
The research was conducted over a four year period from 2016 to 2019 and centred on finger movement, by recording the keystroke dynamics as participants typed on a keyboard. It was proposed that PD could be detected in its early stages through changes in the characteristics of a person’s typing and that such changes could be used to accurately distinguish people with PD from those without. The research involved several hundred anonymous volunteers, who typed normally on their own computer in their home or office, and comprised four separate sub-studies into specific motor features of PD and several alternative detection and assessment methodologies.
Several novel disease detection and classification techniques were developed, and the research met all its objectives – it achieved a high accuracy in detecting early PD in
The detection of movement-related disease ii
subjects, with results better than any existing diagnostic test, and it contributes to the theory and practice of disease diagnosis using HCI. It provides a basis for development of an e-health screening test and, for patients who already have PD, the monitoring of their disease status and progression. The detection techniques do not require any specialised equipment or medical supervision, and do not rely on the experience and skill of the practitioner.

Parkinson's Disease (PD) is a progressive neurodegenerative movement disease affecting over 6 million people worldwide. Loss of dopamine-producing neurons results in a range of both motor and non-motor symptoms, however there is currently no definitive test for PD by non-specialist clinicians, especially in the early disease stages where the symptoms may be subtle and poorly characterised. This results in a high misdiagnosis rate (up to 25% by nonspecialists) and people can have the disease for many years before diagnosis. There is a need for a more accurate, objective means of early detection, ideally one which can be used by individuals in their home setting. In this investigation, keystroke timing information from 103 subjects (comprising 32 with mild PD severity and the remainder non-PD controls) was captured as they typed on a computer keyboard over an extended period and showed that PD affects various characteristics of hand and finger movement and that these can be detected. A novel methodology was used to classify the subjects' disease status, by utilising a combination of many keystroke features which were analysed by an ensemble of machine learning classification models. When applied to two separate participant groups, this approach was able to successfully discriminate between early-PD subjects and controls with 96% sensitivity, 97% specificity and an AUC of 0.98. The technique does not require any specialised equipment or medical supervision, and does not rely on the experience and skill of the practitioner. Regarding more general application, it currently does not incorporate a second cardinal disease symptom, so may not differentiate PD from similar movementrelated disorders.