Here's How AI can now able to detect Depression in a Child's Speech

Here's How AI can now able to detect Depression in a Child's Speech

Researchers have developed an AI-powered system that can identify signs of anxiety and depression in the speech patterns of young children.

Research published in the Journal of Biomedical and Health Informatics reveals that a Machine Learning algorithm can provide a fast and easy way to detect the state of anxiety and depression - conditions that are difficult to find and often overlooked in young people.

PhD candidate in Vermont University in America, Ellen McGinnis said, "We need quick, objective tests to catch the kids when they are suffering from this type of severe illness". McGinniss further added that "Majority of children under the age of eight are undiagnosed."

The initial diagnosis of these conditions is important because at this age their brains are still developing and also the children will react well to the treatment but if they are left untreated, they are at greater risk which may lead to suicide or any mental disease.

For the study, the researchers used a customized version of mood-induction work called Trier-Social Stress Task, whose aim is to generate tension and anxiety feelings in the participants.

The researchers selected a group of 71 children between 3 to 8 years of ages, who were asked to improvise a three-minute story, and told that they would be judged based on how interesting it was. 

Researchers working as judges remained harsh in the whole speech, and only gave neutral or negative feedback.

After every 30 seconds, a buzzer would sound and the judge would tell them how much time was left. "The task is made to be stressful, and to put them in the mindset that someone was judging them," McGinnis said.

The children were also pinpointed using a structured clinical interview and parent questionnaire, both well-established methods of detecting internal disorders in children.

After this few methods, the researchers used a Machine Learning algorithm to scan the statistical characteristics of the audio recordings of each kid's story and to compare them with the diagnosis of the child. Researchers found that the algorithm was highly successful in the diagnosis of children.

Ryan said "Machine Learning algorithm was capable to detect conditions like anxiety and depression in kids with 80% accuracy. And in most cases that compared really well to the accuracy of the parent checklist". 

It has been said in the study that it can give results more quickly - just after the completion of task ( to provide a diagnosis), the algorithm requires a few seconds of processing.

Post a Comment