AI 中文总结
研究利用可微生物物理模拟等从细胞外多电极阵列测量数据快速推断霍奇金-赫胥黎模型参数，用于预测神经尖峰反应，以验证方法收集猕猴视网膜数据，准确率达90.6%。
AI 中文摘要
多室霍奇金-赫胥黎（HH）模型为预测神经动力学和电刺激反应提供框架。但拟合HH生物物理参数通常需侵入性且低通量的细胞内记录。多电极阵列（MEA）提供了可扩展替代方案，但HH模型复杂性阻碍了仅从细胞外数据进行可靠生物物理推断。本文引入框架，通过利用可微生物物理模拟和基于模拟的推断从细胞外MEA测量的设计特征快速推断HH参数，解锁广泛下游应用。在这项工作中，我们专注于转化神经工程的一个核心目标：预测对候选神经刺激模式的神经尖峰反应，这在临床上需要数小时来测量。为了验证我们的方法，我们使用30微米间距的512电极阵列从分离的猕猴视网膜收集了数百小时的刺激和记录数据。我们的框架使用仅从几分钟记录中拟合的HH模型，以90.6%的准确率预测了以前未见过的多电极刺激反应，取代了数小时的刺激测试。
英文摘要
Multi-compartment Hodgkin-Huxley (HH) models provide a principled framework for predicting neural dynamics and responses to electrical stimulation. However, fitting HH biophysical parameters typically requires intracellular recordings, which are invasive and low-throughput, limiting the ability to capture the geometry and cell-specific properties of many neurons in a given neural circuit. Multi-electrode arrays (MEAs) offer a scalable alternative - high-density extracellular measurements from full neural populations, but HH model complexity has so far precluded reliable biophysical inference from extracellular data alone. Here, we introduce a framework to rapidly infer HH parameters from designed features of extracellular MEA measurements by leveraging differentiable biophysical simulation and simulation-based inference, unlocking a wide range of downstream applications. In this work, we focus on a central goal of translational neuroengineering: predicting neural spiking responses to candidate neurostimulation patterns that would take hours to measure clinically. To validate our approach, we collected hundreds of hours of stimulation and recording data from isolated macaque retina with a 30 um-pitch 512-electrode array. Our framework predicted previously unseen multi-electrode stimulation responses with 90.6% accuracy using HH models fit from only a few minutes of recording, replacing hours of stimulus testing.
CommentsAccepted at ICML 2026
