BradyXplore: Bradykinesia Feature Extraction System

BradyXplore：运动迟缓特征提取系统

• 批准号: 8209533
• 负责人: Dustin A. Heldman
• 金额: $ 10.42万
• 依托单位: GREAT LAKES NEUROTECHNOLOGIES
• 依托单位国家: 美国
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-09-30 至 2012-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8209533
• 关键词: BradyXplore; Bradykinesia; Feature; Extraction; System

DESCRIPTION (provided by applicant): The objective is to design, implement, and clinically assess a portable, user worn, bradykinesia feature extraction system, BradyXplore", for easy integration with CleveMed's existing ParkinSense" technology platform. Idiopathic Parkinson's disease (PD) and other parkinsonian disorders affect millions of people. Three major symptoms responsible for functional disability and reduced quality of life include tremor, bradykinesia, and rigidity. The current standard in evaluating symptoms is the Unified Parkinson's Disease Rating Scale (UPDRS), a subjective, qualitative ranking system. While tremor is often the most visible symptom, bradykinesia can be the most impairing to the patient. Objectively quantifying bradykinesia would aid in evaluating treatment protocol efficacy. More specifically, UPDRS scoring instructions for bradykinesia integrates multiple features into a single score that may cause increased inter-rater variability in scores as well as limit the opportunity to explore if particular bradykinesia features are influenced by specific treatment protocols. CleveMed has previously developed a compact wireless system to quantify movement disorder symptoms called ParkinSense". This previously existing technology will serve as the hardware platform for this proposed program. In a clinical study, this system successfully demonstrated objective quantification of PD motor symptoms. Quantitative variables were processed and applied to algorithms to assess symptom severity. Algorithm outputs were highly correlated with clinicians' qualitative UPDRS scores for rest, postural, and kinetic tremor. While moderate results were also achieved for bradykinesia, this application addresses optimization of bradykinesia feature extraction including speed, amplitude, and rhythm. The UPDRS uses three tasks to evaluate bradykinesia severity on a 0-4 scale: finger taps; hand opening- closing; and pronation-supination. Patients are instructed to repetitively complete each task as fast and with as wide an excursion as they can. Clinician scorers are instructed to account for speed, amplitude, fatiguing, hesitations, arrests in movement, and how these variables change over time. Accounting for all of these variables is challenging, even for the most experienced movement disorder specialist. It is difficult to gauge weights specific clinicians place on different bradykinesia manifestations. Also, it is unclear if underlying neural mechanisms for different manifestations are the same. Objectively quantifying specific bradykinesia features should aid in the development of novel DBS therapies for targeting specific bradykinesia manifestations. Furthermore, a portable platform for more continuous monitoring will allow a clinician to capture complex fluctuation patterns in treatment response. PUBLIC HEALTH RELEVANCE: Parkinson's disease affects more than 1,000,000 people in the United States causing motor symptoms of which one of the most debilitating is bradykinesia (slowed movements). Bradykinesia is currently evaluated using a subjective rating scale that gives a single score taking into account speed, amplitude, fatiguing, hesitations, arrests in movement, and how these variables change over time. The proposed BradyXplore bradykinesia feature extraction system will separately quantify specific features of bradykinesia (speed, amplitude, and rhythm), which should aid in the development of novel therapies to target a patient's specific bradykinesia manifestations.

描述（由申请人提供）：目的是设计、实施和临床评估便携式、用户佩戴的运动迟缓特征提取系统“BradyXplore”，以便与CleveMed现有的ParkinSense”技术平台轻松集成。特发性帕金森病（PD）和其他帕金森病影响数百万人。导致功能障碍和生活质量下降的三个主要症状包括震颤、运动迟缓和僵硬。目前评估症状的标准是统一帕金森病评定量表（Unified Parkinson's Disease Rating Scale，简称EADS），这是一种主观的定性评级系统。虽然震颤通常是最明显的症状，但运动迟缓可能是对患者最有害的。客观量化运动迟缓将有助于评估治疗方案的疗效。更具体地说，用于运动迟缓的ECORS评分说明将多个特征整合到单个评分中，这可能导致评分的评分者间变异性增加，并限制探索特定运动迟缓特征是否受特定治疗方案影响的机会。CleveMed先前开发了一种紧凑的无线系统，用于量化运动障碍症状，称为ParkinSense。这一先前存在的技术将作为这一拟议计划的硬件平台。在临床研究中，该系统成功地证明了PD运动症状的客观量化。处理定量变量并应用于算法以评估症状严重程度。算法输出与临床医生的静息、姿势和动力性震颤定性评分高度相关。虽然对于运动迟缓也实现了中等结果，但是本申请解决了运动迟缓特征提取的优化，包括速度、幅度和节律。该量表使用三项任务以0-4量表评估运动迟缓的严重程度：手指轻敲;手张开-闭合;和旋前-旋后。指导患者尽可能快地重复完成每项任务，并尽可能广泛地偏移。指导临床医生评分员考虑速度、幅度、疲劳、犹豫、运动停止以及这些变量如何随时间变化。所有这些变量的会计是具有挑战性的，即使是最有经验的运动障碍专家。这是很难衡量的重量具体临床医生对不同的运动迟缓的表现。此外，目前还不清楚不同表现的潜在神经机制是否相同。客观地量化特定的运动迟缓特征有助于开发针对特定运动迟缓表现的新型DBS疗法。此外，用于更连续监测的便携式平台将允许临床医生捕获治疗响应中的复杂波动模式。公共卫生相关性：帕金森氏病在美国影响超过1，000，000人，引起运动症状，其中最使人衰弱的症状之一是运动迟缓（运动减慢）。运动迟缓目前使用主观评定量表进行评估，该量表考虑到速度，幅度，疲劳，犹豫，运动停滞以及这些变量如何随时间变化而给出单一评分。所提出的运动迟缓特征提取系统将单独量化运动迟缓的特定特征（速度、幅度和节律），这将有助于开发针对患者特定运动迟缓表现的新型疗法。