Science 3 min read

New AI can Detect Depression in Childrens' Speech

Alexas_Fotos / Pixabay

Alexas_Fotos / Pixabay

Depression is the most common mental health disorder in the United States.

But, it’s not just an adult thing: depression also affects infants. More than 16 percent of children in the United States have suffered from anxiety and depression.

Children below the age of eight often have a hard time expressing their emotional state. As such, not only are adults responsible for inferring their kid’s mental state, but they have to look out for potential mental health problems too.

Unfortunately, a lot of grown-ups fail at this responsibility. Alongside parents’ failure to recognize the symptoms, other factors contribute to children missing out on necessary treatment for depression.

These include insurance issues, as well as the waiting list for an appointment with a mental health professional.

Well, there’s good news.

According to a publication in the Journal of Biomedical and Health Informatics, researchers have developed a machine learning algorithm to detect and diagnose depression in children quickly. And all it uses is the child’s speech pattern.

A clinical psychologist at the University of Vermont Medical Center’s Vermont Center for Children, Youth and Families and lead author of the study, Ellen McGinnis said:

“We need quick, objective tests to catch kids when they are suffering… The majority of kids under eight are undiagnosed.”

Since the childrens’ brains are still developing, early diagnosis would enable them to respond well to treatments. However, a child left untreated is at a higher risk of substance abuse and suicide later in life.

Using AI and Machine Learning To Quickly and Reliably Diagnose Depression

The researchers induced a feeling of stress and anxiety on a group of 71 children between the ages of three and eight. They asked the respondents to improvise a three minutes story and judged the stories based on how interesting they were.

Not only were the researchers stern in their speech, but gave only negative or neutral feedbacks. Also, the judge would tell the respondents how much time was left after a specific time.

“The task is designed to be stressful, and to put them in the mindset that someone was judging them,” says Ellen McGinnis.

The children had been diagnosed before-hand using parent questionnaire and clinical interview.

Using the machine learning algorithm, researchers simply analyzed the statistical features of the audio recording of each child’s story, then compared them to the child’s diagnosis.

They discovered that the algorithm’s result was not only accurate, but it produced the result quickly – after a few seconds of processing time.

Co-author Ryan McGinnis noted:

“The algorithm was able to identify children with a diagnosis of an internalizing disorder with 80% accuracy, and in most cases that compared really well to the accuracy of the parent checklist”

The algorithm identified three key features in the children’s speech as a high indicative of depression. These include low-pitched voices, higher-pitched response to the surprising buzzer, and repeatable speech inflections and content.

“A low-pitched voice and repeatable speech elements mirror what we think about when we think about depression: speaking in a monotone voice, repeating what you’re saying,says Ellen McGinnis.

The researcher hopes to put the machine learning algorithm into future smartphones.

That way, the machine learning algorithm can work with motion analysis to quickly identify children at risk of anxiety and depression.

Read More: Researchers Develop New Therapy for Treatment-Resistant Depression

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.