Abstract
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 non-specialists) 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 movement-related disorders.
Highlights
The research problemParkinson’s Disease (PD) is a progressive neurodegenerative movement disease affecting approximately 2% of people at the age of 65 and is the most second most commonly occurring neurodegenerative disease in the elderly, with more than 6.3 million people worldwide with PD [1]
The objective of this research was to identify those characteristics of finger movement which are affected by PD and, through the application of machine learning (ML), to be able to accurately classify the disease status of the participants in the investigation
The machine learning ensemble was run on the Group A datasets and achieved a classification accuracy of 100% compared to the participants’ true disease status (Table 7), and an area under the curve (AUC) of 100% (Fig 6)
Summary
Parkinson’s Disease (PD) is a progressive neurodegenerative movement disease affecting approximately 2% of people at the age of 65 and is the most second most commonly occurring neurodegenerative disease in the elderly (after Alzheimer’s Disease), with more than 6.3 million people worldwide with PD [1]. Diagnosis relies on observation of a combination of visible symptoms by a specialist (typically a neurologist), PD is commonly either misdiagnosed or the diagnosis is missed completely. Specialists who were not movement disorder experts had a correct diagnosis rate of only 75% and diagnoses by primary care doctors had a correct diagnosis of just 53%. A patient may have the disease for 5 to 10 years before it is diagnosed [3] and, by the time of diagnosis, typically 70% of the neurons in the affected part of the brain (the substantia nigra) have already been lost [4]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
