Sendi Mohammad S E, Cole Eric R, Piallat Brigitte, Ellis Charles A, Eggers Thomas E, Laxpati Nealen G, Mahmoudi Babak, Gutekunst Claire-Anne, Devergnas Annaelle, Mayberg Helen, Gross Robert E, Calhoun Vince D
Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, United States.
Department of Electrical and Computer Engineering at Georgia Institute of Technology, Atlanta, GA, United States.
Res Sq. 2024 Sep 4:rs.3.rs-4876094. doi: 10.21203/rs.3.rs-4876094/v1.
Brain stimulation holds promise for treating brain disorders, but personalizing therapy remains challenging. Effective treatment requires establishing a functional link between stimulation parameters and brain response, yet traditional methods like random sampling (RS) are inefficient and costly. To overcome this, we developed an active learning (AL) framework that identifies optimal relationships between stimulation parameters and brain response with fewer experiments. We validated this framework through three experiments: (1) in silico modeling with synthetic data from a Parkinson's disease model, (2) in silico modeling with real data from a non-human primate, and (3) in vivo modeling with a real-time rat optogenetic stimulation experiment. In each experiment, we compared AL models to RS models, using various query strategies and stimulation parameters (amplitude, frequency, pulse width). AL models consistently outperformed RS models, achieving lower error on unseen test data in silico and in vivo . This approach represents a significant advancement in brain stimulation, potentially improving both research and clinical applications by making them more efficient and effective. Our findings suggest that AL can substantially reduce the cost and time required for developing personalized brain stimulation therapies, paving the way for more effective and accessible treatments for brain disorders.
脑刺激有望治疗脑部疾病，但个性化治疗仍然具有挑战性。有效的治疗需要在刺激参数和大脑反应之间建立功能联系，然而像随机抽样（RS）这样的传统方法效率低下且成本高昂。为了克服这一问题，我们开发了一种主动学习（AL）框架，该框架能够通过较少的实验确定刺激参数与大脑反应之间的最佳关系。我们通过三个实验验证了这个框架：（1）使用帕金森病模型的合成数据进行计算机模拟建模，（2）使用非人类灵长类动物的真实数据进行计算机模拟建模，以及（3）通过实时大鼠光遗传学刺激实验进行体内建模。在每个实验中，我们使用各种查询策略和刺激参数（幅度、频率、脉宽）将AL模型与RS模型进行比较。AL模型始终优于RS模型，在计算机模拟和体内的未见测试数据上实现了更低的误差。这种方法代表了脑刺激领域的一项重大进展，有可能通过提高研究和临床应用的效率和有效性来改善它们。我们的研究结果表明，主动学习可以大幅降低开发个性化脑刺激疗法所需的成本和时间，为更有效且可及的脑部疾病治疗铺平道路。
