Scientists at the University of Technology Sydney in Australia have developed the first portable, non-invasive artificial intelligence system that can decode silent ideas and convert them into tangible text, according to a report by Science and Technology Daily, citing a physicist organization network on the 11th. This technology can help people who are unable to speak due to illness or injury, including stroke or paralysis, and is also expected to enable seamless communication between humans and devices such as bionic arms or robots. The latest research represents a groundbreaking effort to translate raw electroencephalography (EEG) directly into language, marking a major breakthrough in the field.

According to a report by the Shanghai Securities Daily on December 1, a few days ago, NetEase's vertical model landed in the medical clinical field for the first time. The world's first multimodal AI epileptiform discharge detection system, vEpiSpy, jointly developed by NetEase Media and Peking Union Medical College Hospital, was officially unveiled at the 26th National Conference on Neurology, and was clinically trialized in many top tertiary hospitals in China, including Peking Union Medical College Hospital, Beijing Tiantan Hospital, and Children's Hospital Affiliated to Shandong University.

In a paper published last month in the journal Nature, the researchers described how they took a deep learning model called the Vision Transformer using an Nvidia GPU, combined with a A rapid-response EEG device to detect delirium symptoms in critically ill elderly patients. The method achieved a test accuracy of 97 percent, promising a breakthrough in predicting dementia. By leveraging AI and EEG, researchers are able to objectively evaluate prevention and treatment approaches, leading to better care.