By Ellen Crown, U.S. Army Medical Materiel Agency Public AffairsJune 6, 2016
Can the acoustics of someone's voice indicate if he or she has a brain injury?
Researchers with the Massachusetts Institute of Technology Lincoln Laboratory (MIT LL) are developing a computer algorithm to identify vocal biomarkers (e.g., indicators) that could help diagnose mild traumatic brain injury (TBI), or concussion.
The U.S. Army Medical Materiel Agency (USAMMA), a subordinate organization of the U.S. Army Medical Research and Materiel Command (USAMRMC), has partnered with MIT LL to help evaluate, test and validate the algorithm. So far, the algorithm has a successful track record in assessing mental or cognitive state from speech. Researchers have used the algorithm to identify a variety of cognitive changes, including those associated with preclinical mild TBI (mTBI) and depression, all based on vocal biomarkers. For example, people with mental or cognitive changes may elongate their syllables and vowel sounds, alter the coordination of their tongue and lip movement, and also struggle with pronouncing phrases that require complex facial muscle movements to sound out. Also, their voice quality may fluctuate, becoming rough or crackly.
"The USAMRMC is very excited to partner with MIT Lincoln Laboratory, expanding upon many efforts currently underway to better diagnose and treat traumatic brain injury," said Dr. Kenneth Bertram, Principal Assistant for Acquisition at the USAMRMC. "If this technology works, it will be incredibly useful to both the military and sports industry, as a decision-aid tool to accurately assess brain injury."
The Centers for Disease Control and Prevention (CDC) define TBI as an injury that results from a blow or jolt to the head or a penetrating head injury that disrupts the normal function of the brain. Since 2000, more than 344,000 service members have been diagnosed with TBI, including mild (e.g. concussion), moderate, and severe. Concussions are the most common form of TBI, according to the Defense and Veterans Brain Injury Center, and may result in headaches, visual disturbances, sleep issues, dizziness, poor concentration and memory problems, and changes to behavior, personality or mood.
Service members are at higher risk for TBI because their jobs are physically demanding and potentially dangerous, both in combat and training environments. However, not all blows or jolts to the head result in TBI. Often military teams must make quick decisions on the training field and the battlefield as to whether a service member who may have sustained a head injury is fit to return to full duty.
"The ultimate goal is a U.S. Food and Drug Administration-cleared, real-time mild TBI screening app and hardware device which can be used throughout the echelons of care from point of injury to rehabilitation. The concept of utilizing vocal recognition as a mild TBI biomarker shows promise in potential fielding applications," said Brian Dacanay, USAMMA product manager.
MIT LL has also reached a licensing agreement with an industry partner for the development of a future portable device, similar to a smart phone, to host the algorithm and allow it to be used as a medical diagnostic device or decision aid. The goal is to get a device ready for U.S. Food and Drug Administration clearance by 2018.
"MIT Lincoln Laboratory is pleased to extend our partnership with the Army to include the NCAA to bring noninvasive, objective biomarkers as a decision aid for such a complex and prevalent injury as TBI using a technology that will have value on the sports field as well as the battlefield," said Dr. Jeffrey Palmer, MIT LL Bioengineering Group Leader.
MIT LL is a federally funded research and development center that applies advanced technology to problems of national security. Research and development activities focus on long-term technology development as well as rapid system prototyping and demonstration. These efforts are aligned within key mission areas. The Laboratory works with industry to transition new concepts and technology for system development and deployment.