Identifying the neurophysiological effects of memory-enhancing amygdala stimulation using interpretable machine learning.
Identifying the neurophysiological effects of memory-enhancing amygdala stimulation using interpretable machine learning.
复制标题
使用可解释的机器学习来识别增强记忆杏仁核刺激的神经生理效应。
DOI：
10.1016/j.brs.2021.09.009
复制
发表时间：
2021-11
影响因子：
7.7
通讯作者：
Mahmoudi, Babak
中科院分区：
文献类型：
--
作者：
Sendi, Mohammad S. E.;Inman, Cory S.;Bijanki, Kelly R.;Blanpain, Lou;Park, James K.;Hamann, Stephan;Gross, Robert E.;Willie, Jon T.;Mahmoudi, Babak
关键词：
对杏仁核的直接电刺激可以增强对特定事件的陈述性记忆。一个尚未回答的问题是杏仁核刺激会引起什么潜在的神经生理学变化。利用可解释的机器学习来识别杏仁核介导的记忆的神经生理过程，并开发更有效的神经调节技术。患有难治性癫痫的患者在海马体和杏仁核中放置深度电极，对物体的中性图像进行识别记忆任务。在编码阶段，向患者展示了160张图像。一半的图像随后是短暂的低振幅杏仁核刺激。对于从关键内侧颞叶结构记录的局部场电位（LFPs），通过在刺激前后在典型频带中的平均谱功率来计算特征向量，以训练具有弹性网络正则化的逻辑回归分类模型来区分大脑状态。根据随后记住的图像和不记得的图像对编码时的神经状态进行分类，结果表明海马体中的θ和慢伽马功率是预测随后记忆表现的最重要特征。根据刺激与未刺激的试验对编码时的后图像神经状态进行分类，结果表明杏仁核刺激导致海马体中伽马能量增加。杏仁核刺激诱导海马中的前记忆状态，以增强随后的记忆表现。可解释机器学习为研究脑刺激的神经生理学效应提供了有效的工具。
Direct electrical stimulation of the amygdala can enhance declarative memory for specific events. An unanswered question is what underlying neurophysiological changes are induced by amygdala stimulation. To leverage interpretable machine learning to identify the neurophysiological processes underlying amygdala-mediated memory, and to develop more efficient neuromodulation technologies. Patients with treatment-resistant epilepsy and depth electrodes placed in the hippocampus and amygdala performed a recognition memory task for neutral images of objects. During the encoding phase, 160 images were shown to patients. Half of the images were followed by brief low-amplitude amygdala stimulation. For local field potentials (LFPs) recorded from key medial temporal lobe structures, feature vectors were calculated by taking the average spectral power in canonical frequency bands, before and after stimulation, to train a logistic regression classification model with elastic net regularization to differentiate brain states. Classifying the neural states at the time of encoding based on images subsequently remembered versus not-remembered showed that theta and slow-gamma power in the hippocampus were the most important features predicting subsequent memory performance. Classifying the post-image neural states at the time of encoding based on stimulated versus unstimulated trials showed that amygdala stimulation led to increased gamma power in the hippocampus. Amygdala stimulation induced pro-memory states in the hippocampus to enhance subsequent memory performance. Interpretable machine learning provides an effective tool for investigating the neurophysiological effects of brain stimulation.
登录
查看更多内容
DOI：
10.1016/j.cub.2017.03.028
发表时间：
2017-05-08
期刊：
Current biology : CB
影响因子：
--
作者：
Ezzyat Y;Kragel JE;Burke JF;Levy DF;Lyalenko A;Wanda P;O'Sullivan L;Hurley KB;Busygin S;Pedisich I;Sperling MR;Worrell GA;Kucewicz MT;Davis KA;Lucas TH;Inman CS;Lega BC;Jobst BC;Sheth SA;Zaghloul K;Jutras MJ;Stein JM;Das SR;Gorniak R;Rizzuto DS;Kahana MJ
通讯作者：
Kahana MJ
影响因子：
2.7
作者：
Bass, David I.;Nizam, Zainab G.;Partain, Kristin N.;Wang, Arick;Manns, Joseph R.
通讯作者：
Manns, Joseph R.
DOI：
10.1073/pnas.1714058114
发表时间：
2018-01-02
影响因子：
11.1
作者：
Inman, Cory S.;Manns, Joseph R.;Willie, Jon T.
通讯作者：
Willie, Jon T.
DOI：
10.1073/pnas.1014528108
发表时间：
2011-06-28
影响因子：
11.1
作者：
Addante, Richard J.;Watrous, Andrew J.;Ranganath, Charan
通讯作者：
Ranganath, Charan
影响因子：
7.7
作者：
Bezaire, Marianne J.;Raikov, Ivan;Soltesz, Ivan
通讯作者：
Soltesz, Ivan