Automated screening for childhood communication disorders

September 22, 2016 by Larry Hardesty, Massachusetts Institute of Technology
A new computer system can automatically screen young children for speech and language disorders and, potentially, even provide specific diagnoses. Credit: Jose-Luis Olivares/MIT

For children with speech and language disorders, early-childhood intervention can make a great difference in their later academic and social success. But many such children—one study estimates 60 percent—go undiagnosed until kindergarten or even later.

Researchers at the Computer Science and Artificial Intelligence Laboratory at MIT and Massachusetts General Hospital's Institute of Health Professions hope to change that, with a computer system that can automatically screen young children for speech and language disorders and, potentially, even provide specific diagnoses.

This week, at the Interspeech conference on speech processing, the researchers reported on an initial set of experiments with their system, which yielded promising results. "We're nowhere near finished with this work," says John Guttag, the Dugald C. Jackson Professor in Electrical Engineering and senior author on the new paper. "This is sort of a preliminary study. But I think it's a pretty convincing feasibility study."

The system analyzes audio recordings of children's performances on a standardized storytelling test, in which they are presented with a series of images and an accompanying narrative, and then asked to retell the story in their own words.

"The really exciting idea here is to be able to do screening in a fully automated way using very simplistic tools," Guttag says. "You could imagine the storytelling task being totally done with a tablet or a phone. I think this opens up the possibility of low-cost screening for large numbers of children, and I think that if we could do that, it would be a great boon to society."

Subtle signals

The researchers evaluated the system's performance using a standard measure called area under the curve, which describes the tradeoff between exhaustively identifying members of a population who have a particular disorder, and limiting false positives. (Modifying the system to limit generally results in limiting true positives, too.) In the medical literature, a diagnostic test with an area under the curve of about 0.7 is generally considered accurate enough to be useful; on three distinct clinically useful tasks, the researchers' system ranged between 0.74 and 0.86.

To build the new system, Guttag and Jen Gong, a graduate student in and computer science and first author on the new paper, used machine learning, in which a computer searches large sets of training data for patterns that correspond to particular classifications—in this case, diagnoses of speech and language disorders.

The training data had been amassed by Jordan Green and Tiffany Hogan, researchers at the MGH Institute of Health Professions, who were interested in developing more objective methods for assessing results of the storytelling test. "Better diagnostic tools are needed to help clinicians with their assessments," says Green, himself a speech-language pathologist. "Assessing children's speech is particularly challenging because of high levels of variation even among typically developing children. You get five clinicians in the room and you might get five different answers."

Unlike speech impediments that result from anatomical characteristics such as cleft palates, and language disorders both have neurological bases. But, Green explains, they affect different neural pathways: Speech disorders affect the motor pathways, while language disorders affect the cognitive and linguistic pathways.

Telltale pauses

Green and Hogan had hypothesized that pauses in children's speech, as they struggled to either find a word or string together the motor controls required to produce it, were a source of useful diagnostic data. So that's what Gong and Guttag concentrated on. They identified a set of 13 acoustic features of children's speech that their machine-learning system could search, seeking patterns that correlated with particular diagnoses. These were things like the number of short and long pauses, the average length of the pauses, the variability of their length, and similar statistics on uninterrupted utterances.

The children whose performances on the storytelling task were recorded in the data set had been classified as typically developing, as suffering from a language impairment, or as suffering from a speech impairment. The machine-learning system was trained on three different tasks: identifying any impairment, whether speech or language; identifying language impairments; and identifying speech impairments.

One obstacle the researchers had to confront was that the age range of the typically developing children in the data set was narrower than that of the children with impairments: Because impairments are comparatively rare, the researchers had to venture outside their target age range to collect data.

Gong addressed this problem using a statistical technique called residual analysis. First, she identified correlations between subjects' age and gender and the acoustic features of their speech; then, for every feature, she corrected for those correlations before feeding the data to the machine-learning algorithm.

"The need for reliable measures for screening young children at high risk for speech and language disorders has been discussed by early educators for decades," says Thomas Campbell, a professor of behavioral and brain sciences at the University of Texas at Dallas and executive director of the university's Callier Center for Communication Disorders. "The researchers' automated approach to screening provides an exciting technological advancement that could prove to be a breakthrough in and language screening of thousands of across the United States."

Explore further: Sign language may be helpful for children with rare speech disorder

Related Stories

Recommended for you

Asteroids, hydrogen make great recipe for life on Mars

March 26, 2019

A new study reveals asteroid impacts on ancient Mars could have produced key ingredients for life if the Martian atmosphere was rich in hydrogen. An early hydrogen-rich atmosphere on Mars could also explain how the planet ...

Cool Earth theory sheds more light on diamonds

March 26, 2019

A QUT geologist has published a new theory on the thermal evolution of Earth billions of years ago that explains why diamonds have formed as precious gemstones rather than just lumps of common graphite.

New cellulose-based material represents three sensors in one

March 26, 2019

Cellulose soaked in a carefully designed polymer mixture acts as a sensor to measure pressure, temperature and humidity at the same time. The measurements are completely independent of each other. The ability to measure pressure, ...

Physicists discover new class of pentaquarks

March 26, 2019

Tomasz Skwarnicki, professor of physics in the College of Arts and Sciences at Syracuse University, has uncovered new information about a class of particles called pentaquarks. His findings could lead to a new understanding ...

Study finds people who feed birds impact conservation

March 26, 2019

People in many parts of the world feed birds in their backyards, often due to a desire to help wildlife or to connect with nature. In the United States alone, over 57 million households in the feed backyard birds, spending ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.