Quadriplegia

TUESDAY, April 1, 2025 -- For nearly two decades, a stroke had left a woman unable to speak -- until now. Thanks to a new brain implant, her thoughts are being turned into real-time speech, giving her a voice again for the first time in 18 years. The device was tested on a 47-year-old woman with quadriplegia who lost her ability to speak after a stroke . Doctors placed the brain-computer implant during surgery as part of a clinical trial, The Associated Press reported. It “converts her intent to speak into fluent sentences,” said Gopala Anumanchipalli , an assistant professor of electrical engineering and computer sciences at UC Berkeley and a co-author of the study published Monday in the journal Nature Neuroscience . Unlike other brain-computer systems that have a delay, this new technology works in real time. Scientists say that the delay in existing systems makes conversations hard and, sometimes, frustrating. Jonathan Brumberg of the Speech and Applied Neuroscience Lab at the University of Kansas, who reviewed the findings, welcomed the advances. This is “a pretty big advance in our field,” he told The Associated Press . Here’s how it works: The team recorded the woman’s brain activity using electrodes as she silently imagined saying sentences. They also used a synthesizer using her voice before her stroke to re-create the sound she would have made. An AI model was trained to translate her brain signals into sounds. The system sends each small sound unit -- roughly a half-syllable -- into a recorder every 80 milliseconds. That means it works quickly, just like real-time transcription on a phone call. “It’s not waiting for a sentence to finish,” Anumanchipalli said. “It’s processing it on the fly.” Decoding speech that fast could help the device keep up with the speed of natural conversation, Brumberg added. Using a person’s actual voice “would be a significant advance in the naturalness of speech.” Though the research was partly funded by the National Institutes of Health, Anumanchipalli said it was not affected by recent cuts to NIH funding. He added that more research is still needed, but with “sustained investments,” the device could be available to patients within 10 years. Whatever your topic of interest, subscribe to our newsletters to get the best of Drugs.com in your inbox.

编辑丨王多鱼排版丨水成文自然的口语交流是瞬间完成的。超过几秒钟的言语迟缓就会打断对话的自然流畅。这使得瘫痪者难以参与有意义的对话，从而可能会导致他们产生孤立和沮丧的感觉。近年来，脑机接口（BCI）领域取得了许多突破性进展，例如，2023 年 8 月，加州大学旧金山分校张复伦（Edward Chang）团队在 Nature 期刊发表论文【1】，通过新型脑机接口（BCI），将因脑干中风而严重瘫痪的患者在大脑中尝试的无声说话转化为文字、语音和图像，从而帮助严重瘫痪者恢复沟通能力。然而，这种面相言语的脑机接口一般在患者尝试无声说话与计算机输出之间会有几秒钟的延迟，这种延迟会在聆听者与患者之间造成交流不畅和困扰。而一个实时系统有望恢复自然对话交流，或能提高失语患者的生活质量。2025 年 3 月 31 日，加州大学旧金山分校张复伦团队与加州大学伯克利分校 Gopala Anumanchipalli 团队合作，在 Nature Neuroscience 期刊发表了题为：A streaming brain-to-voice neuroprosthesis to restore naturalistic communication 的研究论文。该研究开发了一种新型脑机接口设备，在 AI 模型训练的帮助下，能够将瘫痪失语患者大脑中想象的言语活动实时转换成他的声音输出，从而帮助失语者恢复实时流畅交流的能力。在这项研究中，研究体开发了一款无声脑机接口，并作为一个临床试验的一部分，将它植入了一名 47 岁的四肢麻痹（四肢和躯干瘫痪）女性患者的大脑中，这名女性在一次中风发作后已有 18 年无法说话或发声。研究团队让她在大脑中用意念讲出包含 1024 个独特词汇的完整句子，同时用她的大脑活动训练了一个深度学习神经网络，这些大脑活动利用植入该患者言语感觉运动皮质的电极进行记录。研究团队随后使用该模型以 80 毫秒递增的速度解码在线语音，与受试者的发声意图同步，再生成用受试者受伤前说话片段训练的模拟她声音的音频。这个脑机接口还可以推广至该受试者训练中没有接触过的词汇，而且，该设备可以连续不间断使用，而不是每次运行几秒。总的来说，这项研究引入了一种言语-神经假体范式，有望恢复瘫痪失语患者的自然言语交流，让他们更自然流畅地实时说话，从而提高他们的生活质量。论文链接：https://www.nature.com/articles/s41593-025-01905-6设置星标，不错过精彩推文开放转载欢迎转发到朋友圈和微信群 微信加群 为促进前沿研究的传播和交流，我们组建了多个专业交流群，长按下方二维码，即可添加小编微信进群，由于申请人数较多，添加微信时请备注：学校/专业/姓名，如果是PI/教授，还请注明。点在看，传递你的品味

Implantation of a brain-computer interface (BCI) into tetraplegic participants allowed for consistent control of a robotic arm and hand for reaching and grasping, according to a study performed at the University of California San Francisco (UCSF) and published in Cell. Tetraplegia, or quadriplegia, is the paralysis or loss of sensation or function in the cervical area of the spine that affects all four of a person's limbs, both arms and legs. UCSF researchers aimed to study the stability and plasticity of the brain and how it strikes a balance between stable, well-practiced actions and being flexible enough to adjust to new situations quickly. Using a BCI, researchers tracked paralyzed individuals' brain activity while they imagined simple movements. They found that the brain's pattern for these imagined movements remains stable, though it shifted slightly day-to-day. Researchers said the brain could adjust how clearly different movements were represented without changing the overall structure of movement patterns, and the mental representations became sharper in the context of using the BCI. After studying the participants' brain patterns and how they changed over time, researchers identified a "meta-representational structure with generalizable decision boundaries," or a deeper structure in the brain's activity that allowed for long-term neuroprosthetic control of a robotic arm and hand for reaching and grasping. Users had complete voluntary control over the neuroprosthetic, with no help from AI or automation. "This study provides new insights into how the brain maintains stable yet adaptable movement patterns, which could improve long-term control of neuroprosthetic devices," the authors wrote. "Looking ahead, the key challenge for clinically useful BCIs will be balancing long-term stability with the time needed for recalibration." The authors noted that adding vision-based assistance in the future may enhance results, especially for tasks involving complex object interactions. THE LARGER TREND Researchers noted limitations within the study, stating it is unclear how different ECoG grid placements in the brain or different participant groups, such as left-handed individuals, may affect the results. "Moreover, it is unclear whether there is a ceiling in the number of discrete motor commands that can be used for complex hDoF control. In addition, real-time continuous methods to account for drift might also affect our hDoF PnP results," the authors noted. Future studies need to be done to "more directly contrast long-term adaptation of a biomimetic continuous decoder with IBID for overall performance and long-term PnP." Other companies aiming to utilize BCI technology to allow individuals to control robotic body parts include Elon Musk's brain-computer interface implant startup, Neuralink. In November, Neuralink announced on X that it received approval to launch a new feasibility study, CONVOY, which will test the use of its wireless BCIs, or N1 implant, to control an investigational assistive robotic arm. Neuralink's PRIME (short for Precise Robotically Implanted Brain-Computer Interface) study involves the placement of a small, cosmetically invisible implant in the area of a person's brain that plans movements. The N1 implant is designed to interpret one's neural activity to assist them in operating a computer or smartphone by simply intending to move.