"ID";"Original Title";"Title";"Summary";"Contact";"Citation";"URL Scientific Article";"More References";"Keywords";"Field of Research";"Method/Model";"Year of Publication";"Month of Publication";"Date of Editing"; "617";"High-performance brain-to-text communication via handwriting";"Brain-computer interface turns mental handwriting into text";"Using an implanted sensor to record the brain signals associated with handwriting, scientists have developed a brain-computer interface (BCI) designed to restore the ability to communicate in real-time in people with spinal cord injuries and neurological disorders such as amyotrophic lateral sclerosis (ALS). By implanting two small sensors on a patient’s brain, researchers were able to decipher the brain activity associated with trying to write letters by hand. A machine-learning algorithm was used to identify letters as the patient attempted to write them, then the system displayed the text on a screen. Other BCIs for restoring communication exist; however, they have shown to be imprecise and have several limitations. In this study, the participant, whose hand was paralysed from spinal cord injury, achieved typing speeds of 90 characters per minute with 94.1% raw accuracy online, and greater than 99% accuracy offline with a general purpose autocorrect. Researchers hope this technology may one day help restore the ability to communicate with patients with similar problems.";"Francis R. Willett, Stanford University School of Medicine, Stanford, USA";"Francis R. Willett et al. Nature 2021";"https://www.nature.com/articles/s41586-021-03506-2#citeas";"";"machine learning, ALS, multiple sclerosis, neurodegeneration, amyotrophic lateral sclerosis, artificial intelligence";"Method development, Neurology";"Human studies, Epidemiology, In silico, Artificial intelligence";"2021";"05";"2021-07-02 08:10:03";