Wilson Guy H, Willett Francis R, Stein Elias A, Kamdar Foram, Avansino Donald T, Hochberg Leigh R, Shenoy Krishna V, Druckmann Shaul, Henderson Jaimie M
bioRxiv. 2023 Feb 4:2023.02.03.527022. doi: 10.1101/2023.02.03.527022.
Intracortical brain-computer interfaces (iBCIs) require frequent recalibration to maintain robust performance due to changes in neural activity that accumulate over time. Compensating for this nonstationarity would enable consistently high performance without the need for supervised recalibration periods, where users cannot engage in free use of their device. Here we introduce a hidden Markov model (HMM) to infer what targets users are moving toward during iBCI use. We then retrain the system using these inferred targets, enabling unsupervised adaptation to changing neural activity. Our approach outperforms the state of the art in large-scale, closed-loop simulations over two months and in closed-loop with a human iBCI user over one month. Leveraging an offline dataset spanning five years of iBCI recordings, we further show how recently proposed data distribution-matching approaches to recalibration fail over long time scales; only target-inference methods appear capable of enabling long-term unsupervised recalibration. Our results demonstrate how task structure can be used to bootstrap a noisy decoder into a highly-performant one, thereby overcoming one of the major barriers to clinically translating BCIs.
由于神经活动随时间累积的变化，皮层内脑机接口（iBCI）需要频繁重新校准以维持稳健的性能。补偿这种非平稳性将能够实现持续的高性能，而无需监督重新校准期，在此期间用户无法自由使用其设备。在这里，我们引入了一种隐马尔可夫模型（HMM）来推断用户在使用iBCI期间正在朝着哪些目标移动。然后，我们使用这些推断出的目标对系统进行重新训练，从而实现对不断变化的神经活动的无监督适应。在为期两个月的大规模闭环模拟以及与一名人类iBCI用户进行的为期一个月的闭环实验中，我们的方法优于现有技术水平。利用一个跨越五年iBCI记录的离线数据集，我们进一步展示了最近提出的数据分布匹配重新校准方法在长时间尺度上是如何失效的；只有目标推断方法似乎能够实现长期无监督重新校准。我们的结果证明了如何利用任务结构将一个有噪声的解码器引导成一个高性能的解码器，从而克服了脑机接口临床转化的一个主要障碍。
