The brain waves of a paralyzed man transformed into language: it is the first (historic) time

After implanting high-density electrodes on the brain of a paralyzed patient unable to speak intelligibly, a team of neurosurgeons and engineers from the University of California at San Francisco for the first time was able to transform brain waves into language. , allowing the communication of entire sentences through a screen.

Thanks to a revolutionary “neuroprotesi” a paralyzed man for over 15 years and unable to speak in an intelligible way it has recovered (in part) the lost language. For the first time in the history of scientific research, in fact, an electronic device has managed to convert the brain waves in complete sentences, which were transcribed on the computer screen after decoding. Unlike the research conducted to date in this field, the electrical signals linked to the movement of the arm or hand to allow the typing of single letters, one at a time, but i have been exploited brain signals intended to control the muscles of the voice system that we use to pronounce words. This approach allows for “faster, more organic and natural” communication by processing entire sentences.

To place this milestone in scientific research was a team of doctors and researchers from the University of California San Francisco (UCSF) led by neurosurgeon Edward Chang, who for over ten years has been involved in the development of a technology that can allow people paralyzed and unable to speak to return to communicate. In fact, every year thousands of people lose the ability to speak due to stroke, accidents O illnesses, but in the future, thanks to the evolution of the neuroprosthesis, these people could return to “fully communicate”.

It all began with research on patients with epilepsy, in which Dr. Chang and colleagues from UCSF Weill Institute for Neurosciences had implanted electrode array in brain to investigate the causes of their condition. The patients, with perfectly normal language, agreed to have the tests analyzed registrations of the brain waves associated with language, allowing aartificial intelligence to identify “patterns” related to words. The next step was to apply what was learned about the patient “BRAVO1”, A 36-year-old man who at the age of 20 suffered a very serious stroke; the event irremediably damaged the connection between the brain, vocal muscles and limbs. Man suffers from anartria, a condition that makes it difficult or impossible articulate sounds of the voice. In other words, the words expressed by the patient are not understandable.

For the first time we have observed the merger between a black hole and a neutron star

Professor Chang and his colleagues, within the research project “Brain-Computer Interface Restoration of Arm and Voice” (BRAVO), collaborated with the man to fine-tune 50 parole fundamental for his life – such as water, hunger, family etc etc – to make them recognizable by computer algorithms. After the surgical implantation of high-density electrodes on the patient’s speech motor cortex, the scientists recorded 22 hours of neuronal activity in dozens of sessions, during which BRAVO1 tried to repeat each of the above 50 words. In this way it was possible to train an artificial intelligence to recognize and decode the brain waves emitted by the patient during the attempts, which were subsequently translated into words on a computer screen. The interesting aspect is that the system, unlike the other approaches, is able to process entire sentences, albeit short. “The system was able to decode words from brain activity at a speed of up to 18 words per minute, with an accuracy of up to 93 percent (median 75 percent),” the study authors wrote. All this also thanks to a sort of automatic corrector similar to those for writing on smartphones.

“As far as we know, this is the first successful demonstration of direct decoding of complete words from the brain activity of someone who is paralyzed and cannot speak,” said Professor Chang. “It shows strong promise of restoring communication by tapping into the brain’s natural speech mechanism,” added the scientist. The details of the research were reported in a press release from the University of San Francisco and in an editorial published in The New England Journal of Medicine, the most authoritative scientific journal in the medical field.

!function(f,b,e,v,n,t,s) {if(f.fbq)return;n=f.fbq=function(){n.callMethod?
s.parentNode.insertBefore(t,s)}(window, document,’script’,
fbq(‘init’, ‘2062554930705272’);
fbq(‘track’, ‘PageView’);
//fbq(‘track’, ‘ViewContent’);
//send custom checkpoints event
(function () {
var checkPoints = [10, 20, 40, 60, 90, 120, 180, 240, 300].sort(function(a, b) {
return a – b;
}); //seconds
var checkPointIndex = 0;
var f = function(){
var data = {
instant: checkPoints[checkPointIndex]
console.log(“[FB PIXEL] send custom event ViewContentCheckPoint “, data, ” on account ” ,”2062554930705272″ , ” currentTime in seconds “,
new Date().getTime() / 1000);
fbq(‘trackCustom’, ‘ViewContentCheckPoint’, data);
if(checkPointIndex < checkPoints.length) {
setTimeout(f, (checkPoints[checkPointIndex] – checkPoints[checkPointIndex-1]) * 1000)
setTimeout(f, checkPoints[checkPointIndex] * 1000)


Disclaimer: If you need to update/edit/remove this news or article then please contact our support team Learn more

Leave a Reply