Scientists have developed an AI-powered approach that significantly improves the precision of experimental bionic vision technology, according to research published this week. The system works by learning how an individual's brain responds to electrical stimulation, allowing it to predict the flashes and shapes of light perceived by a blind man fitted with a brain implant. By modelling the unique neural response patterns of each patient, the technology addresses one of the central challenges of bionic vision: the wide variability in how implanted electrodes produce visual percepts. Researchers say the advance marks a meaningful step toward restoring some degree of sight to people living with blindness, though the work remains at an experimental stage.
The findings add to a growing body of research exploring the intersection of artificial intelligence and neuroprosthetics. Bionic vision systems typically bypass damaged optic nerves by stimulating the visual cortex directly, but the resulting perceptions have historically been imprecise and difficult to control. The AI-driven method could enable more tailored calibration of implants, potentially improving the clarity and usefulness of artificial vision for individual users. Scientists caution that larger trials and long-term studies are needed before the technology can be considered for clinical use. Independent experts described the results as promising while noting that significant technical and regulatory hurdles remain before such systems reach patients.
Independent reporting synthesized from primary wires and global correspondents.