Skip to Content

Voice-Analyzing App Scans Football Players for Concussion

Notre Dame researchers will test a concussion-detection app on nearly a thousand high school and youth football players.
September 18, 2013

A voice-analysis program run on a tablet could help high school and youth coaches recognize concussions on the sidelines of football and other high-impact sport games.

After identifying concussions in collegiate boxers in a preliminary study, University of Notre Dame researchers will soon test the app on approximately 1,000 youth and high school football players. The program pulls out the vowel segment from a set of predetermined words and then analyzes that sound for changes that may indicate a brain injury.

Despite all the attention given to the issue in recent years, concussions are still a “highly underrecognized injury,” says Gerry Gioia, a pediatric neuropsychologist at Children’s National Medical Center in Washington, D.C.

The Centers for Disease Control and Prevention (CDC) estimates that as many as 3.8 million sports-related concussions occur in the U.S. each year; but because concussion can go undiagnosed, the true number of such injures could be much higher. Most concussions are not accompanied by loss of consciousness, and the variety of symptoms can be subtle and difficult to spot. But catching concussion can be critically important for athletes, since it can put them at greater risk for another injury. Problems with memory and mental agility associated with concussion get worse with repeated concussions.

“The issue is omnipresent, but when it actually happens, it’s not uncommon for parents or coaches to get confused about what they should really be looking for,” Gioia says. Working with the CDC, Gioia has developed a question-and-answer style app to guide parents or coaches through potential symptoms of concussion and what they should do next. While professional and collegiate football teams have physicians and athletic trainers waiting on the sidelines to run psychological and cognitive tests on players who have taken a heavy hit, youth and high school teams usually do not. Gioia’s app provides a checklist of signs and symptoms to determine whether a player needs to stop playing and go see a doctor.

Researchers at Notre Dame wanted a test for concussion that could not be swayed by answers from a player who wants to stay in the game. Graduate student Nikhil Yadav designed a diagnostic tool that requires someone to simply speak into a mobile device such as a tablet.

Previous studies have found that head injuries change speech characteristics, with negative effects on vowel production in particular. The researchers initially tested the app with 125 boxers participating in a collegiate competition. Before any bouts started, the researchers recorded each boxer saying the numbers one through nine as a baseline. After boxing, the researchers recorded the athletes saying the same words again. By analyzing several acoustic features of the vowel sounds, including their pitch, the app was able to identify all nine players who were later diagnosed with concussion.

“The preliminary results were very promising,” Yadav says. The test wasn’t perfect, however; it also falsely identified concussions in three boxers. “That’s low in this early stage, but we don’t want to see false positives,” says Yadav. He hopes to fine-tune the test to minimize them.

Now, Yadav and colleagues are kicking off a large test of the system with youth and high school football players. They will work with around 1,000 kids between the ages of 10 and 18 in 20 different schools and clubs in Indiana, Illinois, Wisconsin, and Michigan. Any predicted concussions will be compared to medical diagnoses.

If the app proves its worth in this larger test, the researchers plan to turn it into a commercial product through a startup called Contect.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.