appConfigEntityId

bodyType

customContents

entityId

entityUuid

isVideo

articlePageQuery

article

articleSchemaContent

content

hooksArticlePageAdvertisementConfigArticle

hooksArticlePageFloatingButtonConfigArticle

appConfig

filter

json

liveArticle

Shi Huang

Chinese scientists have developed an AI model they say could be used to predict the risk of depression up to four years in advance.
Major Depressive Disorder affects over 332 million people worldwide, according to the researchers at Shenzhen University, and is notoriously difficult to treat.
The ability to predict the risk of depression and take preventive measures could prove a significant public health benefit.
The model was built using data from two clinical trials on adolescent depression conducted in several European countries.
In one study, the participants underwent follow-up examinations – consisting of MRI scans, blood tests and questionnaires – at the ages of 16, 19 and 23 to determine whether they had depression.
The Chinese team analysed this data before using it to design an artificial intelligence model used to detect depression risks.
Using this final model, researchers were able to predict who at the age of 19 was more likely to suffer from depression at the age of 23 – predictions backed up by the final trial data.
To build the model, they tested the trial subjects’ responses to images such as people’s faces as well as their brain signal reactions.
According to the Shenzhen team, people without depression can easily distinguish emotional changes based on others’ facial expressions and respond accordingly – for example, responding with friendliness to a smiling expression.
But people with depression cannot do this, and are more likely to assume people are angry with them.
“These findings suggest a possible mechanism linking genetic vulnerability to altered emotion perception and future depression, and propose a predictive computational marker with potential for early detection and prevention,” Lu Han, an associate professor at Shenzhen University’s School of Artificial Intelligence wrote.
The team’s paper, published in the journal Science Advances this month, said “deficient emotional processing is a hallmark feature of depression”, adding that individuals with depression show signs of “always assuming the worst in others.”
The main study, known as Imagen, looked at a group of adolescents across four European countries, starting in 2007, and primarily observed the progression of depression.
During the study, magnetic resonance imaging scans were carried out on the teenagers while they were shown images of angry, happy, and neutral faces.


A targeted analysis of their brain activity by Lu’s team concluded that those participants whose brains could not distinguish between different facial emotions and tended to perceive others as angry were significantly more likely to experience symptoms of depression and anxiety in adulthood.
Building on this, they created a deep learning model, which mimics how the brain processes visual information, to predict how the brain encodes abstract emotional concepts such as anger.
They found that 19-year-olds whose response to facial expressions was skewed in favour of negative emotions or memories were the most likely to develop some form of depression.
Lu then developed a marker based on these research findings and applied it to the participants in a second trial, Stratify, which compared depression with other mental disorders, such as alcoholism, binge eating or drug abuse.
The results showed that among a cohort of over 400 adolescents with various forms of depression, only those with a clinical diagnosis of major depressive disorder – 134 in total – had abnormal readings.
However, the results for patients with symptoms such as addiction, anorexia and bulimia showed little difference from those with no signs of mental health problems.
Passionate about science? Dive deeper with the Dark Matters newsletter, a weekly in-depth analysis on China’s rise in science, technology and military that goes beneath the surface. Sign up for free now.


China tests first practical submarine solar power plant at 10-metre depth in the open sea

Rare earth exposure can triple low birthweight risk: Chinese study

China must enforce high standards of integrity for scientists

Is China’s fabled Empress Dowager Huayang buried near an airport? A study says yes

Science

Chinese brain-reading AI model may help predict depression risk 4 years in advance

Researchers carried out MRI scans on the trial participants to see how they responded to facial expressions. Photo: Shutterstock

China is pitching its AI models to Europe, but is it enough to avoid 2-horse race with US?

China is seeking closer cooperation with European countries on AI. Photo: Xinhua

Chinese team’s wearable dopamine patch could be used to track depression, Parkinson’s

Abnormal dopamine levels are associated with neurological conditions including Parkinson’s disease and depression. Image: Shutterstock

The wearable sensor uses microscopic needles to test fluid just beneath the skin. Photo: Handout

News

China

Scientists from Shenzhen University used data studying teenagers’ responses to facial expressions to identify possible warning signs


Scientists from Shenzhen University used data studying teenagers’ responses to facial expressions to identify possible warning signs.


Shenzhen

Artificial intelligence (AI)

Chinese brain-reading AI model may help predict depression risk 4 years in advance

.css-1c6uqr6{color:inherit;font-weight:inherit;font-size:inherit;font-family:inherit;line-height:inherit;overflow-wrap:break-word;}Scientists from Shenzhen University used data studying teenagers’ responses to facial expressions to identify possible warning signs

Scientists from Shenzhen University used data studying teenagers’ responses to facial expressions to identify possible warning signs