Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Award Abstract # 1448930
STTR Phase I: Development and Validation of a Speech-Based Portable Concussion Screening Tool

NSF Org: TI
Translational Impacts
Recipient:
Initial Amendment Date: December 18, 2014
Latest Amendment Date: December 18, 2014
Award Number: 1448930
Award Instrument: Standard Grant
Program Manager: Jesus Soriano Molla
jsoriano@nsf.gov
 (703)292-7795
TI
 Translational Impacts
TIP
 Dir for Tech, Innovation, & Partnerships
Start Date: January 1, 2015
End Date: December 31, 2015 (Estimated)
Total Intended Award Amount: $224,918.00
Total Awarded Amount to Date: $224,918.00
Funds Obligated to Date: FY 2015 = $224,918.00
History of Investigator:
  • Shane McQuillan (Principal Investigator)
    smcquillan@contectinc.com
  • Christian Poellabauer (Co-Principal Investigator)
Recipient Sponsored Research Office: Contect, Inc.
4637 N Central Park
Chicago
IL  US  46617-1368
(773)405-9859
Sponsor Congressional District: 02
Primary Place of Performance: Contect, Inc.
1400 E. Angela Blvd
South Bend
IN  US  46617-1370
Primary Place of Performance
Congressional District:
02
Unique Entity Identifier (UEI): QADUW24AYRZ1
Parent UEI:
NSF Program(s): STTR Phase I
Primary Program Source: 01001516DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 124E, 1505, 5345, 8038, 8042
Program Element Code(s): 150500
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.041

ABSTRACT

The broader impact/commercial potential of this Small Business Technology Transfer (STTR) Phase I project is found in the creation of a faster, more portable, affordable, and reliable concussion screening tool. This is important because of the large number of concussions occurring during youth sport events (estimates range between 2 and 4 million cases per year) and the potential longterm health problems of concussions. The primary concept behind this technology is the collection of brief speech samples using the microphone of a portable device and the instant speech analysis that informs a physician or athletic trainer of significant deviations of certain speech patterns. With widespread use, this technology will make detection of concussions easier and faster and will allow injured athletes to obtain appropriate treatment as quickly as possible. The addressable market for this technology in just the U.S. and E.U. athletic market segments is $6B. This estimate is based on a competitive price point compared to existing concussion screening tools. Additionally, this technology helps address the overall economic impact of untreated concussions, which is estimated to be more than $60B annually.

The proposed project will play a key role in the development of a novel concussion screening tool based on speech as a biomarker. Currently, almost 90% of concussions remain undetected, primarily due to the lack of easytouse, rapid, and accurate testing tools. The project will provide a deeper understanding of the relationship between brain injuries and their impacts on speech production, and how to build a toolkit to measure these changes. This STTR team?s Phase I research project will lead to the development of speech processing algorithms on mobile devices, capable of measuring speech changes in any setting. Once the tool is developed a proof of concept study will be undertaken which will compare physician diagnosed concussions versus the Contect test. The fundamental goal

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Christian Poellabauer, Nikhil Yadav, Louis Daudet, Sandra Schneider, Carlos Busso, and Patrick Flynn "Challenges in Concussion Detection Using Vocal Acoustic Biomarkers" IEEE Access , v.3 , 2015 , p.1143
Christian Poellabauer, Nikhil Yadav, Patrick Flynn, and Sandra Schneider "Using Speech Analysis for TBI Detection" Proceedings of INFORMS Healthcare , 2015
Nikhil Yadav, Christian Poellabauer, Louis Daudet, Tomas Collins, Shane McQuillan, Patrick Flynn, and Sandra Schneider "Portable Neurological Disease Assessment Using Temporal Analysis of Speech" Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics , 2015

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

There are reportedly about 42 million individuals in the U.S. who exhibit deficits in speech, language, voice, or hearing. Motor speech disorders are considered the result of neurological impairments affecting the motor planning and coordination or the strength of the articulators needed to generate effortless and smooth speech. The most common underlying causes for motor speech disorders are traumatic brain injuries, stroke, or neurodegenerative diseases such as Parkinson’s Disease. It is the task of practitioners such as speech-language pathologists to determine what assessments should be made to detect the presence and severity of a motor speech disorder and then to determine the most efficacious treatment for that specific speech disorder. However, the assessment of the motor speech system is a complex and challenging task. Currently, perceptual methods are the most common way speech language pathologists detect, identify, and judge the presence of a speech disorder. This involves making judgments of the salient features (i.e., strength, speed of movement, range of movement, accuracy, steadiness, tone) of speech production. The accuracy of such judgment depends on the level of experience, listening skills, observational skills, and potential bias of the practitioner. Therefore, there is a need for objective measures and tools to maximize the accuracy of identification.

 

In this project, a prototype of a motor speech disorder test for portable devices was developed and tested. This test requires an individual to go through a series of reading tasks, where the voice of the individual is continuously recorded for analysis. Further, the project investigated various speech processing strategies and acoustic features in speech that can be used to detect or assess a speech disorder and the potential underlying cause. Initial tests on 18 subjects (including 9 Parkinson’s patients) provided evidence that the test is able to distinguish between healthy individuals and individuals with a motor speech disorder. Overall, the primary merits of this project are in the development of the motor speech disorder test, the study of the links between impaired brain functioning and speech, and the evaluation of the test using Parkinson’s patients. The project also provided undergraduate and graduate students with research opportunities and the results of the project are also used for lecture materials and projects in several courses.


Last Modified: 02/06/2016
Modified by: Christian Poellabauer