The detection of movement-related disease by changes in keystroke characteristics while typing

Parkinson’s Disease (PD) is a progressive neurodegenerative movement disease affecting over 1% of people by the age of 60 and is the second most commonly occurring neurodegenerative disease in the elderly, with an estimated 6 million sufferers worldwide (as at 2017). The loss of dopamine-producing neurons in PD results in a range of both motor (that is, referring to motion) and non-motor symptoms, and currently a patient can have the disease for 5 to 10 years before it is diagnosed, by which time the majority of the neurons in the affected part of the brain may have already been lost. At present, diagnosis of PD relies on observation of patient movement and in a clinical setting it is commonly misdiagnosed or missed completely – with primary care doctors making an incorrect diagnosis more than half of the time and only movement disorder specialists achieving reliable diagnostic accuracies.
The problem which was addressed in this research was the need for more accurate and objective diagnoses of PD, particularly in its early stages where the observable symptoms may be subtle and imprecise. In order to be effective, such a technique would need to be significantly more accurate than current non-specialist clinician diagnoses; provide quantitative and repeatable results; be able to detect PD where there are just mild symptoms present; and not to require specialised equipment.
The research was conducted from 2016 to 2019 and centred on finger movement, by recording the keystroke dynamics as participants typed on a computer keyboard. It was proposed that PD could be detected 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. It achieved both a high accuracy and a low rate of false positives in detecting early PD in subjects, using several novel disease detection and classification techniques.
This research addressed a significant problem in human health and has contributed to the theory and practice of disease diagnosis, through using human-computer interaction (HCI) to measure and characterise movement dynamics and, in particular, their changes in people with PD. It provides the basis for development of an e-health screening test and, for patients who already have PD, the monitoring of their disease status and progression.