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.

Public Health Relevance

Traumatic brain injury (TBI) is a serious public health problem in the United States contributing to a substantial number of deaths and cases of permanent disability. Mild TBI concussions account for over 80% of all TBIs sustained and a major problem is the high rate of mis-diagnosis due to lack of objective measures and delayed onset of symptoms. This project aims to develop the first objective concussion evaluation method using a novel analysis platform that can obtain subtle, physiologic changes in cerebral hemodynamics. Successful completion of this project will result in a portable diagnostic device suitable for use in many scenarios where concussion diagnosis is inaccurate or unavailable today.

Agency
National Institute of Health (NIH)
Institute
National Institute of Neurological Disorders and Stroke (NINDS)
Type
Small Business Innovation Research Grants (SBIR) - Phase II (R44)
Project #
5R44NS092209-03
Application #
9323604
Study Section
Special Emphasis Panel (ZRG1)
Program Officer
Fertig, Stephanie
Project Start
2015-06-01
Project End
2019-07-31
Budget Start
2017-08-01
Budget End
2019-07-31
Support Year
3
Fiscal Year
2017
Total Cost
Indirect Cost
Name
Neural Analytics, Inc.
Department
Type
DUNS #
078766464
City
Los Angeles
State
CA
Country
United States
Zip Code
90064
Thibeault, Corey M; Thorpe, Samuel; O'Brien, Michael J et al. (2018) A Cross-Sectional Study on Cerebral Hemodynamics After Mild Traumatic Brain Injury in a Pediatric Population. Front Neurol 9:200
Rajagopal, Abhejit; Hamilton, Robert B; Scalzo, Fabien (2016) Noise reduction in intracranial pressure signal using causal shape manifolds. Biomed Signal Process Control 28:19-26
Quachtran, Benjamin; Hamilton, Robert; Scalzo, Fabien (2016) Detection of Intracranial Hypertension using Deep Learning. Proc IAPR Int Conf Pattern Recogn 2016:2491-2496