Automated deep brain stimulation programming with safety constraints for tremor suppression in patients with Parkinson's disease and essential tremor.
Automated deep brain stimulation programming with safety constraints for tremor suppression in patients with Parkinson's disease and essential tremor.
复制标题
DOI：
10.1088/1741-2552/ac86a2
复制
发表时间：
2022-08-18
影响因子：
4
通讯作者：
Miocinovic, Svjetlana
中科院分区：
文献类型：
--
作者：
Sarikhani, Parisa;Ferleger, Benjamin;Mitchell, Kyle;Ostrem, Jill;Herron, Jeffrey;Mahmoudi, Babak;Miocinovic, Svjetlana
深部脑刺激(DBS)治疗运动障碍需要系统地微调刺激参数，以缓解震颤和其他症状，同时避免副作用。DBS规划可能是一个耗时的过程，需要临床专业知识来评估对DBS的反应，以优化每个患者的治疗。在这项研究中，我们描述和评估了一种用于DBS编程的自动化、闭环和特定于患者的框架，该框架使用智能手表测量震颤，并根据来自闭环优化算法的建议自动更改DBS参数，从而消除了对专家临床医生的需求。贝叶斯优化是一种样本效率高的全局优化方法，它作为DBS编程框架的核心，自适应地学习每个患者对DBS的反应，并建议下一个需要评估的最佳设置。临床医生的输入最初用于定义最大安全幅度，但我们也实施了“安全贝叶斯优化”，以自动发现可容忍的勘探边界。我们在15名患者中测试了该系统(9名帕金森氏症患者和6名特发性震颤患者)。在最好的自动化设置下，震颤抑制与先前建立的临床设置在统计上具有可比性。当预定义最大安全勘探边界时，优化算法收敛到15.1±0.7设置；当算法本身确定安全勘探边界时，优化算法收敛到17.7±4.9。我们证明，用于震颤治疗的全自动DBS编程框架是有效和安全的，同时提供的结果与专家临床医生所取得的结果相当。
Deep brain stimulation (DBS) programming for movement disorders requires systematic fine tuning of stimulation parameters to ameliorate tremor and other symptoms while avoiding side effects. DBS programming can be a time-consuming process and requires clinical expertise to assess response to DBS to optimize therapy for each patient. In this study, we describe and evaluate an automated, closed-loop, and patient-specific framework for DBS programming that measures tremor using a smartwatch and automatically changes DBS parameters based on the recommendations from a closed-loop optimization algorithm thus eliminating the need for an expert clinician. Bayesian optimization which is a sample-efficient global optimization method was used as the core of this DBS programming framework to adaptively learn each patient’s response to DBS and suggest the next best settings to be evaluated. Input from a clinician was used initially to define a maximum safe amplitude, but we also implemented ‘safe Bayesian optimization’ to automatically discover tolerable exploration boundaries. We tested the system in 15 patients (nine with Parkinson’s disease and six with essential tremor). Tremor suppression at best automated settings was statistically comparable to previously established clinical settings. The optimization algorithm converged after testing 15.1 ± 0.7 settings when maximum safe exploration boundaries were predefined, and 17.7 ± 4.9 when the algorithm itself determined safe exploration boundaries. We demonstrate that fully automated DBS programming framework for treatment of tremor is efficient and safe while providing outcomes comparable to that achieved by expert clinicians.
登录
查看更多内容
DOI：
10.1111/ner.13350
发表时间：
2021-03
期刊：
Neuromodulation : journal of the International Neuromodulation Society
影响因子：
--
作者：
Noecker AM;Frankemolle-Gilbert AM;Howell B;Petersen MV;Beylergil SB;Shaikh AG;McIntyre CC
通讯作者：
McIntyre CC
影响因子：
4
作者：
Duchet B;Weerasinghe G;Bick C;Bogacz R
通讯作者：
Bogacz R
影响因子：
16.6
作者：
Boutet A;Madhavan R;Elias GJB;Joel SE;Gramer R;Ranjan M;Paramanandam V;Xu D;Germann J;Loh A;Kalia SK;Hodaie M;Li B;Prasad S;Coblentz A;Munhoz RP;Ashe J;Kucharczyk W;Fasano A;Lozano AM
通讯作者：
Lozano AM
DOI：
10.3390/s17092067
发表时间：
2017-09-09
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Jeon H;Lee W;Park H;Lee HJ;Kim SK;Kim HB;Jeon B;Park KS
通讯作者：
Park KS
影响因子：
4.1
作者：
Sasaki, Fuyuko;Oyama, Genko;Hattori, Nobutaka
通讯作者：
Hattori, Nobutaka