Technology Review - Published By MIT
Advertisement

A Device to Spot Autism Early

A new system automatically analyzes vocalizations for signs of autism.

By Rachel Kremen

Tuesday, September 15, 2009

smaller text tool iconmedium text tool iconlarger text tool icon

Researchers have developed a device that can automatically identify autistic children as young as 24 months using the vocalizations they make during a normal day at home. Instead of waiting months or years for an appointment with a specialist, parents could get an objective diagnosis by mail in a couple of weeks.

Sound system: The LENABaby system uses a digital recording device to capture up to 16 hours of audio, which is then analyzed to diagnose autism and language delays.
Credit: LENA Foundation

According to a recent study from researchers at Washington University in St. Louis, the average age of diagnosis for autism is 5.7 years old -- several years after such a diagnosis is first possible. With the new system, developed at the LENA Foundation, diagnosis takes just a few weeks. "Intervention is most effective when the child is two to four years old," says Jill Gilkerson, director of child language research at the LENA Foundation.

The foundation says its tool can distinguish, with 91 percent accuracy, between a child developing normally, a child with autism, and a child with unassociated language delays.

The home kit, called LENABaby, hit the market earlier this month and consists of a questionnaire regarding the child's development, a digital audio recorder, and an outfit for the child to wear. First thing in the morning, the parent puts the outfit on the child and slides the recorder into a pocket on the front. The recorder is left on all day so that it can capture up to 16 hours of audio. At the end of the day, the parent removes the device from the pocket and sends it to the foundation, where the LENABaby software can analyze the data.

"Roughly speaking, autistic children vocalize differently from other children," explainsDongxin Xu,manager of software and language engineering at the LENA Foundation. While this concept isn't new, clinicians have had a hard time using it to their best advantage when making a diagnosis. The problem is, in part, logistical: with existing methods, it is hard to collect enough good-quality data.

Story continues below


Gilkersonsays that most traditional assessments take less than four hours. LENABaby, in contrast, considers a full day of activities in the child's natural environment. Traditional assessments can be done in the child's home, but this often involves multiple video cameras and lights, which can influence the child's behavior.

Even if enough data is gathered, analyzing the audio is still extremely difficult and time-consuming. Making a diagnosis isn't as simple as counting the number of times the child makes a certain kind of sound, explains Jeffrey Richards, a statistician and database technician for the LENA Foundation.

Comments

  • What is the Evidence?
    This reads like a Press Release!

    Shouldn't the article have given SOME hint about What is the Evidence that vocalizations differ between autistic and normal children?

    And, what are the number of false positives and false negatives from using this technique, using clinical data as the standard of comparison?
    Rate this comment: 12345

    hsfrey
    09/15/2009
    Posts:13
    Avg Rating:
    4/5
  • Re: specificity and sensitivity
    Research on the automatic autism screen is ongoing.  Preliminary results
    with 159 children (75 diagnosed with ASD) 24-48 months of age indicate
    the following (assuming equal error rate): sensitivity (.91);
    specificity (.91); positive predictive value (.90); negative predictive
    value (.92).  A detailed technical report will be posted on
    lenafoundation.org in October.  More detailed technical information can
    also be obtained from LENA Foundation on request at:
    info@lenafoundation.org
    Rate this comment: 12345

    miamoe
    09/15/2009
    Posts:1
    Avg Rating:
    5/5
  • Where's the data?
    There is no real data. This has all the hallmarks scam like the places that diagnose autism by analyzing the kids' hair. They claim similar numbers.  That this is being sold as a diagnostic tool before it has been tested marks these people as irresponsible and unethical.  Of course, since it's autism, anything goes.
    Rate this comment: 12345

    fear-teagais...
    09/17/2009
    Posts:1
    Avg Rating:
    5/5
  • [no subject]
    "University of Washington in St. Louis"???

    how about getting the name of the school right?

    Washington University... in St. Louis

    no of, nothing to do with the University of Washington, halfway across the country from that state and in existence decades before the state.
    Rate this comment: 12345

    cowsandmilk
    09/18/2009
    Posts:5
    Avg Rating:
    4/5

Log In

Forgot your password?     Register »
Advertisement

Videos

Malleable Maps, Artistic Robots and Bubble Interfaces
Technology Review January/February 2010

Current Issue

Security in the Ether
Information technology's next grand challenge will be to secure the cloud--and prove we can trust it.
Advertisement
Advertisement
Advertisement
Subscribe to Technology Review's daily e-mail update. Enter your e-mail address

TECHNOLOGY RESOURCES

More Technology News from Forbes

Advertisement
MIT Massachusetts Institute of Technology © 2010 Technology Review. All Rights Reserved.