A Data Science Approach To Personalizing Sensorimotor Training Post-Stroke

中风后个性化感觉运动训练的数据科学方法

• 批准号: 10592727
• 负责人: Olivier Remy-Neris
• 金额: $ 71.67万
• 依托单位: UNIVERSITY OF SOUTHERN CALIFORNIA
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-15 至 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10592727
• 关键词: Acute; Adjuvant; Adjuvant Therapy; Algorithms; Bayesian Modeling; Brain imaging; Characteristics; Clinic; Clinical; Clinical Data; Clinical Trials; Cohort Studies; Collaborations; Corticospinal Tracts; Data; Data Science; Databases; Development; Dose; Exhibits; Functional Magnetic Resonance Imaging; Funding; Future; Hand; Hospitals; Impairment; Individual; Infrastructure; Intelligence; Intervention; Knowledge; Learning; Lesion; Locomotion; Los Angeles; Magnetic Resonance Imaging; Measurement; Measures; Methods; Modeling; Motor; Movement; Neurologic; Outcome; Participant; Patients; Persons; Phase; Process; Prospective cohort study; Quality Control; Recovery; Rehabilitation therapy; Research; Rest; Schedule; Spinal cord injury; Stroke; System; Testing; Time; To specify; Training; Traumatic Brain Injury; Update; Upper Extremity; Work; Wrist; acute stroke; arm; arm movement; base; cohort; conventional therapy; data quality; dosage; exoskeleton; functional outcomes; hemiparesis; imaging science; improved; multidisciplinary; neurological rehabilitation; novel; optimal treatments; post stroke; predictive modeling; public database; rehabilitation research; relating to nervous system; response; routine care; scale up; sensor; simulation; sound; stroke recovery; stroke rehabilitation; treatment effect; treatment response

Project Summary The large variability in lesions, impairment, and responsiveness to therapy following stroke has hindered the development of principled and effective approaches to neurorehabilitation of the upper extremity (UE). Here, building on our multidisciplinary expertise in large-scale neurorehabilitation studies, brain imaging, and data science, as well as our established collaborations, we propose a novel self-improving personalized rehabilitation system based on a continuous loop between data, algorithm, and treatment. In Aim 1, we will create and simulate a self-improving algorithm for personalized UE rehabilitation, based on the state-of-the-art and theoretically-sound “Bayesian contextual bandits” algorithm. A predictive dynamics model will generate time- varying predictions of the UE functional outcome (the ARAT) at 3 months post-stroke in response to training and based on the patient baseline clinical and neural variables that modulate the effects of treatment, and on prior knowledge from similar patients. Second, a sequential-decision bandit algorithm will use the model’s predictions for different (simulated) doses to select the weekly dose that is predicted to maximize the ARAT at 3 months post-stroke, given constraints on the feasible doses. In Aim 2, we will conduct a cohort study of 400 individuals with sub-acute stroke. The detailed treatment, neural, and clinical data generated by this study will allow us to identify the clinical and neural modulators of sensorimotor training as well as the feasible doses in sub-acute stroke. In particular, treatment data will include the schedule of arm movements recorded via an exoskeleton during mechanized adjuvant therapy and the number of hand movements both during and outside conventional therapy recorded with a wrist-worn sensor. In Aim 3, we will perform a proof-of-concept study of the self-improving precision neurorehabilitation system, with 150 participants in the sub-acute phase post-stroke. The algorithm of Aim 1 will determine the optimal weekly doses based on previous measurements of the actual doses, the measured ARAT, and the participant clinical and neural context. This Aim will start in year 3 after the data from 200 participants in Aim 2 have been collected to update the algorithm of Aim 1. The data generated by this Aim will continuously be used to update the model of Aim 1, yielding better predictions and thus more effective schedules of weekly doses. We will therefore test the hypothesis that the change in ARAT from baseline to 3-month will be significantly greater for each new group of 50 participants compared to the previous group. Upon completion of this research, we will have captured a comprehensive picture of rehabilitation treatment parameters that most improve UE function given the heterogeneous profiles after stroke. The resulting unique database of 550 participants, which will be made publicly available, is expected to become a reference in neurorehabilitation and stroke research. The proposed work will lay groundwork for a self- improving algorithm to be used in routine care, which could be scaled up through the StrokeNet infrastructure with future funding.

项目摘要 中风后病变、损伤和治疗反应性的巨大差异阻碍了 制定原则性和有效的方法，上肢神经康复（UE）。在这里， 基于我们在大规模神经康复研究、脑成像和数据方面的多学科专业知识， 科学，以及我们建立的合作，我们提出了一种新的自我改善个性化康复 系统基于数据、算法和治疗之间的连续循环。在目标1中，我们将创建和 基于最新技术和模拟个性化UE康复的自我改进算法 理论上合理的"贝叶斯语境强盗"算法一个预测动力学模型会产生时间- 卒中后3个月时UE功能结局（ARAT）对训练的不同预测， 基于调节治疗效果的患者基线临床和神经变量，以及先前的 类似患者的知识。其次，顺序决策强盗算法将使用模型的预测 对于不同的（模拟）剂量，以选择预测在3个月时使ARAT最大化的每周剂量 中风后，考虑到可行剂量的限制。在目标2中，我们将对400名 亚急性中风患者。本研究生成的详细治疗、神经和临床数据 将使我们能够确定感觉运动训练的临床和神经调节剂以及可行的剂量 亚急性中风特别地，治疗数据将包括经由微处理器记录的手臂运动的时间表。 外骨骼在机械化辅助治疗和手运动的数量都在和外部 传统的治疗记录与腕戴式传感器。在目标3中，我们将进行概念验证研究 自我改进的精确神经康复系统，150名参与者处于亚急性期 中风后目标1的算法将根据先前的测量结果确定最佳每周剂量 实际剂量、测量的ARAT以及参与者的临床和神经背景。这一目标将开始于 目标2中200名参与者的数据收集后第3年，更新目标1的算法。的 该目标产生的数据将不断用于更新目标1的模型，从而产生更好的预测结果 从而更有效的每周剂量的时间表。因此，我们将测试假设， 对于每个新的50名受试者组，从基线到3个月的ARAT将显著高于 前一组。完成这项研究后，我们将全面了解 考虑到中风后的异质性，最能改善UE功能的康复治疗参数。 由此产生的550名参与者的独特数据库将向公众开放，预计将成为 神经康复和中风研究的参考。拟议的工作将为自我- 改进算法，用于常规护理，可通过StrokeNet基础设施扩大规模 未来的资金。