Depression may live in the brain, but scientists have developed a new smartphone app to detect the disorder by looking for clues on the face.
MoodCapture uses AI to evaluate microchanges in a person’s face, such as their gaze, eye movement, and how the person tilts their head, to determine if they were depressed.
The app, funded by the National Institutes of Health, takes photos with the front camera and sends an alert if it identifies a trend in facial expressions by observing the position of participants’ lips, eyes and depression lines. her face.
According to the study, MoodCapture was correct in identifying people with depression 75 percent of the time.
MoodCapture identified whether participants had depressive symptoms based on their facial features, lighting, and background objects.
About eight percent of American adults are diagnosed with depression each year, representing approximately 21 million Americans.
More research still needs to be done, but researchers said MoodCapture could be available to the public as soon as five years from now.
“This is the first time that natural images have been used to predict depression,” said Andrew Campbell, lead author of the study and professor of computer science at Dartmouth College.
“People use facial recognition software to unlock their phones hundreds of times a day,” he said.
“MoodCapture uses similar facial recognition technology with deep learning and AI hardware, so there is huge potential to scale this technology without any additional input or burden on the user.”
The study broke down participants’ facial expressions by looking at the angle of their features, such as how their eyebrows wrinkled, how they tilted their head, and whether their lips were tilted up or down.
Over time, the app noticed patterns that were specific to the user and correctly identified users who often had a flat expression (their features did not change) and were in a dimly lit room for an extended period of time as having depression. .
An estimated 60 percent of people diagnosed with depression do not seek help
The researchers recruited 181 participants in the US who had major depressive disorder according to a questionnaire they were asked to complete.
Participants received three daily surveys to assess their mood, and MoodCapture discreetly took up to five photographs when participants answered a specific question such as “I have felt low, depressed, or hopeless.” to see if I could correctly identify that feeling.
“We chose this question because we believed it would better capture participants’ genuine emotions related to depression,” the study stated.
The images were taken randomly with the front camera over 90 days and observed specific facial expressions of 177 participants, including gaze, eye movement, lighting, how the person positioned their head and others.
Researchers collected a total of 125,335 images, but omitted 15,063 photos that were too blurry, did not show a face, showed children or contained nudity.
MoodCapture analyzed the dominant colors in the participant’s environment, the lighting conditions, the location where the photo was taken (whether indoors or outdoors), any background objects that could be used to measure the user’s activities, and the number of people in the image.
Details like dim lighting can reveal information about a person’s mental state.
MoodCapture can sequence images in real time, combining facial features and background information to predict the severity of your depression.
The researchers asked a series of questions to determine if the person had depressive symptoms and connected this to the MoodCapture findings.
MoodCapture not only identified whether the participant was experiencing depressive symptoms, but also suggested preventative measures such as going outside or asking a friend for help.
“Telling someone that something bad is happening to them has the potential to make things worse,” said Nicholas Jacobson, co-author of the study and assistant professor of biomedical data science and psychiatry at Dartmouth’s Behavioral Health and Technology Center.
“We believe MoodCapture opens the door to screening tools that would help detect depression in the moments before it worsens,” Jacobson said.
Major depression affects more than eight percent of American adults each year, representing approximately 21 million people, but an estimated 60 percent of people diagnosed with depression do not seek professional support, according to health line.
The researchers said the study results were promising, and while more research needs to be done, Campbell said they estimate this technology could be available within the next five years, adding, “We have shown that this is feasible.”
“This shows the way toward a powerful tool to passively assess a person’s mood and use the data as a basis for therapeutic intervention.”
However, the researchers advised that MoodCapture, and any other similar app, should not be used alone, but rather should be combined with other interventions for people with depression.
“Our goal is to capture changes in symptoms that people with depression experience in their daily lives,” Jacobson said.
“If we can use this to predict and understand rapid changes in depression symptoms, we will ultimately be able to prevent and treat them.
“The more in this moment we can be, the less profound the impact of depression will be.”