权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Advanced morphological analysis of cerebral blood flow for acute concussion diagnosis and return-to-play determination

用于急性脑震荡诊断和重返赛场确定的脑血流高级形态学分析

基本信息

批准号：
9323604
负责人：
Robert Hamilton
金额：
$ 150万
依托单位：
NEURAL ANALYTICS, INC.
依托单位国家：
美国
项目类别：
财政年份：
2015
资助国家：
美国
起止时间：
2015-06-01 至 2020-01-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/9323604
关键词：
Accident and Emergency department Acute Adoption Algorithmic Software Algorithms Area Under Curve Assessment tool Blood flow Brain Concussion Cerebrovascular Circulation Cessation of life Classification Clinic Clinical Clinical Data Clinical Research Collaborations Communities Complex Computer software Controlled Study Core-Binding Factor Data Data Analytics Data Collection Development Devices Diagnosis Diagnostic Diagnostic Procedure Evaluation Functional disorder Future Goals Gold Guidelines Health Personnel Hospitals Image Impairment Injury Letters Licensing Machine Learning Magnetic Resonance Imaging Measures Methods Modeling Morphology Neurocognitive Neurologist Neurology Outcome Patients Pediatric Neurology Performance Persons Phase Physical Performance Physicians Physiological Play Public Health Publications Readiness Recovery Research Resolution Risk Severities Shapes Site Small Business Innovation Research Grant Spin Labels Sports Sports Medicine Symptoms Syndrome System Technology Testing Time Training Traumatic Brain Injury Ultrasonography United States Variant balance testing base brain health cerebral hemodynamics clinical Diagnosis diagnostic accuracy disability experimental study hemodynamics high school injured innovation mild traumatic brain injury novel pediatric department performance tests portability prevent programs relating to nervous system success tool

项目摘要

Project Summary / Abstract Between 1.6 and 3.8 million people each year suffer a mild TBI in the US alone. Reliable diagnosis and prompt treatments are vital to managing the often-serious short and long-term sequelae resulting from mild TBI. However, a reliable objective and accurate method for mild TBI diagnosis outside of a hospital setting, and in particular for determining RTP readiness, has eluded the clinical community. Current diagnosis and RTP assessments are based on patient symptoms, neurocognitive evaluations, and / or physical performance testing. Use of symptom scales are problematic for several reasons including subjectivity and reliability. Neurocognitive evaluations and physical tests (such as balance tests), although less subjective, require pre- injury baseline testing of subjects due to inherently large subject-to-subject variations in evaluation performances. Due to these reasons, current mild TBI diagnostic methods have limited applications and are not suitable for a significant majority of patients who suffer mild TBI. This project is aimed at developing an objective diagnosis of mild traumatic brain injury (mild TBI) based on physiologic changes in a patient after injury and providing a platform capable of RTP guidance. The method is based on quantification of well-known physiologic changes after a concussion, i.e. the impairment of autonomic function and altered cerebral blood flow (CBF) as measured with transcranial Doppler (TCD). The novelty of the proposed approach is the use of a recently-developed analytical machine learning framework for the analysis of the CBF velocity (CBFV) waveforms. In contrast to previous methods used before, the proposed approach utilizes the entire shape of the complex CBFV waveform, thus obtaining subtle changes in blood flow that are lost in other analysis methods. Additionally, comprehensive verification between our platform and MRI will be performed following injury resulting in the first scientific experiments of this kind. The ultimate goal of this Phase II SBIR is to commercialize an objective and accurate software algorithm for reliable diagnosis and management of sports concussions which does not currently exist. The outcome will be a software suite integrated into existing TCD and will be marketed to emergency departments, neurology clinics, and other healthcare providers involved in mild TBI diagnosis and RTP management.

项目总结/摘要仅在美国，每年就有160万至380万人患有轻度TBI。可靠的诊断和迅速治疗对于管理由轻度TBI引起的经常严重的短期和长期后遗症至关重要。然而，一个可靠的客观和准确的方法，轻度TBI诊断医院以外的环境，并在特别是用于确定RTP准备就绪，已经回避了临床社区。当前诊断和RTP 评估基于患者症状、神经认知评估和/或身体表现试验.由于主观性和可靠性等原因，症状量表的使用存在问题。神经认知评估和身体测试（如平衡测试），虽然主观性较低，但需要预先检查。由于评价中受试者之间固有的较大差异，受试者的损伤基线测试表演由于这些原因，目前的轻度TBI诊断方法具有有限的应用，不适合大多数轻度TBI患者。该项目旨在开发一个客观的诊断轻度创伤性脑损伤（轻度TBI）的基础上，生理变化的患者受伤后，并提供一个平台，能够RTP指导。该方法基于脑震荡后众所周知的生理变化的量化，即自主神经功能的损害，经颅多普勒（TCD）测量功能和脑血流量（CBF）改变。的新奇所提出的方法是使用最近开发的分析机器学习框架，分析CBF速度（CBFV）波形。与以前使用的方法相比，该方法利用复杂CBFV波形的整个形状，从而获得血流的细微变化在其他分析方法中丢失的信息。此外，我们的平台和MRI之间的全面验证将在第一次此类科学实验中受伤后进行。第二阶段SBIR的最终目标是商业化一个客观和准确的软件算法，目前尚不存在的运动性脑震荡的可靠诊断和管理。结果会一套软件集成到现有的TCD中，并将销售给急诊科、神经科、诊所和其他参与轻度TBI诊断和RTP管理的医疗保健提供者。