How a keyboard can be used to detect Parkinson’s symptoms

Researchers have developed a technique for monitoring the progression of Parkinson’s disease using keystrokes as a diagnostic tool.

“This approach uses something we do normally — interacting with a digital device — so it does not add any additional burden or take time away from daily activities,” explains Luca Giancardo, a former Catalyst Fellow in the Madrid-MIT M+Vision Consortium in the Research Laboratory of Electronics at MIT, and one of the paper's lead authors.

At present, the severity of Parkinson’s signs is determined by trained medical professionals who assess the patient’s ability to perform a range of movement activities. The problem with this approach is that the actual tests take place in a clinical setting, which limits the number of times they can be undertaken.

To improve upon the frequency of these tests, the researchers sought a method that would more naturally allow for the daily monitoring of possible Parkinson’s symptoms, and they honed in on the keyboard as an ideal resource for this data. Specifically, what they’re looking at is the amount of time it takes a user to press down and release each key while typing an email, updating a Facebook status, etc. It’s a technique that’s been used in the past for spotting such ailments as sleep inertia, or grogginess after being suddenly woken up (there’s a general decline of motor dexterity that occurs).

The computer used to carry out this study was installed with software designed to measure the timing of each press and release. In total, 42 patients with early stage Parkinson’s disease and 43 healthy subjects were tasked with typing out a text of their choosing for 10-15 minutes on this computer. 

When the researchers analyzed the data, a significant variation in timing was discovered in patients with early stage Parkinson’s disease, as opposed to the control group, which was much more uniform. 

“By looking at the variation of this press and release, we were able to find a signature that allows us to detect Parkinson's disease in our cohort,” explains Giancardo.

The software used for the experiments can be easily installed as a program on any standard computer, or added to the hardware of a device; in fact, it can even be deployed as a webpage. 

“We envisage that this could be used to fill in the gaps between visits to the neurologist, for example, or between other tests that cannot be carried out continuously,” says Giancardo.

Álvaro Sánchez-Ferro, joint lead author and a former Catalyst Fellow in the Madrid-MIT M+Vision Consortium, explains: “The problem is that so far there has not been an easy method to provide this early detection, and one reason is that the progression of the disease is very slow.” He adds that by monitoring patients on a daily basis, doctors will also be able to more accurately prescribe effective dosage of medication. 

“At present the ability to monitor the motor signs of those with Parkinson's or those who are starting to develop the disease is limited to a clinical setting,” explains Bryan Strange, director of the Laboratory for Clinical Neuroscience within the Technical University of Madrid's Center for Biomedical Technology, in Spain. 

“This [test] is not something that requires the patient to do something out of the ordinary,” he concludes.

Looking ahead, the team hopes their technique could be used to create algorithms that better detect signs of other neurological or motor-based disorders. 

Via MIT