top of page

Scientists can read your inner thoughts with 80% accuracy, study finds

Caltech neuroscientists have made significant strides in developing a brain-machine interface (BMI) to help patients who have lost the ability to speak
Caltech neuroscientists have made significant strides in developing a brain-machine interface (BMI) to help patients who have lost the ability to speak. (CREDIT: Creative Commons)

Caltech neuroscientists have made significant strides in developing a brain-machine interface (BMI) to help patients who have lost the ability to speak. This technology, which implants directly into the brain, aims to enable communication through thought alone, without the need for vocalization or miming.


In 2022, the team achieved a milestone by successfully implanting their BMI in a patient who then communicated unspoken words. Recently, they reported in Nature Human Behaviour that a second patient has also successfully used the BMI, marking a crucial step forward in their research.


 
 

"We are very enthusiastic about these new findings," says Richard Andersen, the James G. Boswell Professor of Neuroscience at Caltech. Andersen, who also directs the Tianqiao and Chrissy Chen Brain-Machine Interface Center, highlighted this achievement in a public lecture. "We reproduced the results in a second individual, which means that this is not dependent on the particulars of one person's brain or where exactly their implant landed. This is indeed more likely to hold up in the larger population."



BMIs are being explored for various applications, including controlling robotic limbs and predicting speech from brain signals in motor areas. However, interpreting internal dialogue—essentially decoding thoughts—presents a greater challenge because it does not involve any physical movement.


 
 

Sarah Wandelt, lead author of the new paper and a neural engineer at the Feinstein Institutes for Medical Research, explains this complexity.


The latest research from Caltech represents the most precise attempt yet to predict internal speech. The team recorded brain signals from single neurons in the supramarginal gyrus, part of the posterior parietal cortex (PPC), a region previously identified as being involved in spoken word representation.


 

Related Stories

 

In the study, the BMI device was trained to recognize brain patterns associated with internally spoken words. This training, conducted with two tetraplegic participants, took only about 15 minutes.


Participants were then shown words on a screen and asked to "say" the words internally. The BMI algorithms predicted the eight tested words, including two nonsensical words, with an average accuracy of 79 percent and 23 percent for the two participants, respectively.


 
 

"Since we were able to find these signals in this particular brain region, the PPC, in a second participant, we can now be sure that this area contains these speech signals," says David Bjanes, a postdoctoral scholar in biology and biological engineering and a co-author of the paper. "The PPC encodes a large variety of different task variables. You could imagine that some words could be tied to other variables in the brain for one person. The likelihood of that being true for two people is much, much lower."



Though still in its early stages, this research holds promise for patients with brain injuries, paralysis, or neurological diseases like amyotrophic lateral sclerosis (ALS) that impair speech. "Neurological disorders can lead to complete paralysis of voluntary muscles, resulting in patients being unable to speak or move, but they are still able to think and reason. For that population, an internal speech BMI would be incredibly helpful," Wandelt says.


 
 

The researchers emphasize that BMIs cannot read minds; they must be individually trained for each user and require focused thought on specific words to function. This promising technology could eventually provide a vital communication tool for those who cannot speak, bringing hope to many patients and their families.





For more science stories check out our New Discoveries section at The Brighter Side of News.


 

Note: Materials provided above by The Brighter Side of News. Content may be edited for style and length.


 
 

Like these kind of feel good stories? Get the Brighter Side of News' newsletter.


 

Comentarios


Los comentarios se han desactivado.

Most Recent Stories

bottom of page