Merk Timon, Köhler Richard M, Brotons Toni M, Vossberg Samed Rouven, Peterson Victoria, Lyra Laura Freire, Vanhoecke Jojo, Chikermane Meera, Binns Thomas S, Li Ningfei, Walton Ashley, Neudorfer Clemens, Bush Alan, Sisterson Nathan, Busch Johannes, Lofredi Roxanne, Habets Jeroen, Huebl Julius, Zhu Guanyu, Yin Zixiao, Zhao Baotian, Merkl Angela, Bajbouj Malek, Krause Patricia, Faust Katharina, Schneider Gerd-Helge, Horn Andreas, Zhang Jianguo, Kühn Andrea A, Mark Richardson R, Neumann Wolf-Julian
Movement Disorder and Neuromodulation Unit, Department of Neurology, Charité - Universitätsmedizin Berlin, Berlin, Germany.
Department of Neurosurgery, Baylor College of Medicine, Houston, TX, USA.
Nat Biomed Eng. 2025 Sep 24. doi: 10.1038/s41551-025-01467-9.
Brain-computer interface research can inspire closed-loop neuromodulation therapies, promising spatiotemporal precision for the treatment of brain disorders. Decoding dynamic patient states from brain signals with machine learning is required to leverage this precision, but a standardized framework for invasive brain signal decoding from neural implants does not exist. Here we develop a platform that integrates brain signal decoding with magnetic resonance imaging connectomics and demonstrate its use across 123 h of invasively recorded brain data from 73 neurosurgical patients treated with brain implants for movement disorders, depression and epilepsy. We introduce connectomics-informed movement decoders that generalize across cohorts with Parkinson's disease and epilepsy from the United States, Europe and China. We reveal network targets for emotion decoding in left prefrontal and cingulate circuits in deep brain stimulation patients with major depression. Finally, we showcase opportunities to improve seizure detection in responsive neurostimulation for epilepsy. Our study highlights the clinical use of brain signal decoding for deep brain stimulation and provides methods that allow for rapid, high-accuracy decoding for precision medicine approaches that can dynamically adapt neurotherapies in response to the individual needs of patients.
脑机接口研究能够推动闭环神经调节疗法的发展，有望为脑部疾病的治疗带来时空精准性。要利用这种精准性，就需要运用机器学习从脑信号中解码动态的患者状态，但目前尚不存在用于从神经植入物进行侵入性脑信号解码的标准化框架。在此，我们开发了一个将脑信号解码与磁共振成像连接组学相结合的平台，并在73名因运动障碍、抑郁症和癫痫而接受脑植入物治疗的神经外科患者的123小时侵入性记录脑数据中展示了该平台的应用。我们引入了基于连接组学的运动解码器，该解码器在来自美国、欧洲和中国的帕金森病和癫痫患者队列中具有通用性。我们揭示了重度抑郁症深部脑刺激患者左前额叶和扣带回回路中用于情绪解码的网络靶点。最后，我们展示了在癫痫的响应性神经刺激中改善癫痫发作检测的机会。我们的研究突出了脑信号解码在深部脑刺激中的临床应用，并提供了一些方法，能够实现快速、高精度的解码，以用于精准医学方法，从而根据患者的个体需求动态调整神经疗法。
