AI Science Tracker

A neuroprosthesis restores words for a man with paralysis

UC San Francisco · 14 Jul 2021 · medicine

Discovery

UC San Francisco

A neuroprosthesis restores words for a man with paralysis

Neural networks decoded the attempted speech of a man with stroke-related paralysis, displaying words and sentences on a screen. With a 50-word vocabulary, the system reached up to 18 words per minute and a median accuracy of 75%. Proof of principle in one person, using an implant on the brain surface and a limited vocabulary.

Technology: Neural networks for speech and language model

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

Result, AI contribution and limits

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

  • Publication status: Peer-reviewed paper
  • Test type: direct test
  • Tested: Decoding was tested in one participant over 48 sessions using a 50-word vocabulary, reaching up to 18 words per minute and a median accuracy of 75%.
  • Still unknown: It is a proof of principle in one person with a limited vocabulary, per the press release.
  • AI role: Deep-learning algorithms decoded attempted words from cortical activity.

Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI%3A10.1056/NEJMoa2027540&resultType=core&format=json

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: press release. Paper: linked separately.

Review scope and date are not recorded; source checked does not establish full-text review.

Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 616 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.

Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Follow-up and relationships

No follow-up recorded; this is not a claim that no follow-up exists.

Follow-up review scope and date are not recorded.

No source-supported relationships recorded.

Open in the full catalog for filters, charts and related discoveries.