April 9, 2015

Will How People Type on their Keyboards Become a Revolutionary New Tool to Detect Parkinson’s – and Begin Treatment -- Sooner?

A new study draws an intriguing conclusion: the WAY people type on their keyboards could become a new clinical tool for much earlier diagnoses of Parkinson’s disease (PD).

Now, there’s no effective way to diagnose PD in its early stages… a delay that carries a big price. Study leader Luca Giancardo said: “People are usually diagnosed five to 10 years after the beginning of the disease, and a lot of the damage has already been done.”

A product of the Madrid-MIT M+Vision Consortium, the study was published last week in the online journal Scientific Reports. Its conclusions are based on a simple premise: the attributes of a person’s keystrokes provide lots of potentially useful information. Of particular interest was a feature the research team called “key hold time,” which measures how long a key is pressed before being released.

These measurements somehow gauge the complex mechanisms that generate movement, as the brain’s primary motor cortex sends signals through several other brain regions, including the supplementary motor area, cerebellum, and basal ganglia. That process then activates spinal neurons which stimulate muscles, creating the movement.

First, the Impact of Fatigue
The initial phase of this study was designed to assess the effects of fatigue on motor ability, but it became apparent it might have broader implications.

To determine the impact of sleep deprivation, the researchers recruited 14 healthy Boston-area volunteers and asked them to type a randomly chosen Wikipedia article.

The subjects were informed they’d be awakened during the night to type another article. About 80 minutes after they had dozed off -- when they’d likely be in the deepest part of their sleep cycle – the volunteers were awakened to complete their next typing assignment.

To evaluate the keystroke elements, the team had developed a plug-in software component that could be easily incorporated into a web browser. Alvaro Sanchez-Ferro, another author of the study, said “We thought this was a unique opportunity to have a window into the brain using your normal interactions with an electronic device.”

The most telling observations concerned the timing of the subjects’ keystrokes. When they were alert during the day, there was little variation in the timing of their keystrokes. When they were roused suddenly from sleep, the timing of their keystrokes showed much more variation.

Next, Parkinson’s
While there’s a world of difference between fatigue and Parkinson’s disease, both have clear effects on motor skills. If keystroke data can indicate neural impairment from fatigue, could the information also signal the presence of Parkinson’s in its early stages?

A very small study suggests it just might.

The team studied 21 people with PD and 15 healthy subjects. The keystrokes of the PD group – like the sleep-interrupted volunteers -- showed significantly more variation than their counterparts in the control group. Those results begged the question: can the keystroke-measuring software become sophisticated enough to recognize even the slightest variations that would begin appearing in the typing of someone with early PD?

The research team members suggest that if these findings can be reconfirmed in larger studies, their keystroke data might well lead to earlier diagnoses of PD, and the initiation of treatments sooner in the disease’s progress.

Beyond Parkinson’s
Study team member Sanchez-Ferro said their keystroke assessment might have application in evaluating – even diagnosing – people with other movement-related conditions and diseases, like rheumatoid arthritis: “This might have applications in any disease producing a motor impairment, whether it’s in your hands and muscles or the brain.”

John Growdon, director of the Memory and Movement Disorders Unit at Massachusetts General Hospital, offered the usual cautions about the need for additional study. Still, he said: “Overall, it strikes me that this has great potential to detect subtle motor impairments even in advance of a clinician’s ability to find them.”

 <>  <>  <>  <>  <>  <>  <>

The information in this post is based on the April 1 news release from MIT. That document also includes a video in which two of the researchers explain in more detail how keyboard strokes reveal psycho-motor interruptions that occur in fatigued people and also people with PD.

No comments: