Two individuals with paralysis have managed to type on a virtual keyboard thanks to an implant that decodes attempted finger movements. One patient typed 80% faster than a healthy individual, according to a study in Nature Neuroscience.
Traditionally, brain-computer interfaces (BCI) for paralysed individuals rely on eye-tracking or recognising neural activity associated with speech. However, researchers from Mass General Brigham and Brown University suggested that the familiar QWERTY keyboard format might be more convenient for many users.
“The most important thing is to have a range of options for each patient to tailor the technology to the specific condition and situation,” noted study author Justin Jude.
In the study, participants were asked to simulate typing on a QWERTY keyboard. The system reliably read brain impulses, recognising up to 30 different actions—three for each of the ten fingers.
Two individuals participated in testing the BCI device from Blackrock Neurotech:
- Patient T17 (paralysed below the neck due to a spinal cord injury) achieved a speed of 47 characters per minute with 81% accuracy;
- Patient T18 (suffering from amyotrophic lateral sclerosis, ALS) recorded a result of 110 characters per minute with 95% accuracy.
The stability of the second individual’s results lasted for a week, whereas the first’s lasted for two days.
Jude noted that the higher performance of one participant might be explained by the number and placement of electrodes in the brain. T18 had six arrays of contacts implanted in the dorsal (upper) part of the precentral gyrus—approximately three times more compared to T17.
For the latter, some electrodes were also placed in other areas of the motor cortex to collect speech signals.
Differences in results may also be explained by the fact that tetraplegia and ALS affect the brain differently, although both conditions lead to paralysis.
Jude emphasised that decoding finger movement signals could help in the future to restore complex hand movements, including grasping and reaching for objects.
In the future, precise recognition of finger motor skills could help restore patients’ ability to control prosthetics for complex manipulations like grasping and reaching for objects.
However, the technology must overcome significant regulatory hurdles before it becomes accessible to a wide range of patients.
In March, China’s regulator approved the country’s first neuroimplant for commercial use.
