-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
-
Cosmetic Ingredient
- Water Treatment Chemical
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
A variety of diseases can cause the loss of language ability caused by brain damage, including stroke and amyotrophic lateral sclerosis.
At present, many auxiliary communication methods can help patients with brain injury and language loss to restore their communication ability, which greatly improves the autonomy and life of patients Quality, but the method of decoding words and sentences directly from the patient’s cerebral cortex activity is a more advanced and effective means of auxiliary communication
.
Recently, researchers carried out the BRAVO experiment to turn this idea into reality
The method of decoding words and sentences directly from the activity of the cerebral cortex of the patient is a more advanced and effective method of auxiliary communication
The subject of this study is a 36-year-old man.
At the age of 20, he suffered severe paralytic quadriplegia and arthritis due to a cerebral stroke in the right vertebral artery and lost language ability, but his cognitive function was intact and his mental status was checked.
The table (0-30, the higher the score, the better the cognitive ability) score is 26 points
.
Researchers implanted a subdural, high-density, multi-electrode array on the patient's sensorimotor cortex
With this method, the researchers decoded the sentences that the participants wanted to express in real time at an average speed of 15.
2 words per minute, with a word error rate of 25.
6%
.
Post-mortem analysis showed that the model detected 98% of the individual words that the participants tried to express.
The researchers decoded the sentences that participants wanted to express in real time at an average speed of 15.
After long-term training, the model's cortical activity signal decoding accuracy changes
This study realized for the first time that in patients with paralysis caused by brainstem stroke, the use of deep learning models and natural language models to directly decode cortical activity to restore the patient's language function
This study is the first realization that in patients with paralysis caused by brainstem stroke, by using deep learning models and natural language models to directly decode cortical activity to restore the patient’s language function .
Original source:
David A.
Neuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria.
Leave a message here
