Researchers from MIT just created an app that can detect depression in people based on their natural conversational and writing style.
“The first hints we have that a person is happy, excited, sad, or has some serious cognitive condition, such as depression, is through their speech,” said Tuka Alhanai, the project’s lead researcher. “If you want to deploy [depression-detection] models in scalable way … you want to minimize the amount of constraints you have on the data you’re using. You want to deploy it in any regular conversation and have the model pick up, from the natural interaction, the state of the individual.”
The team calls the model “context-free” because no constraints are imposed on the types of questions asked or the response that the app is looking for. The app utilizes sequence modeling to use text and audio from depressed and non-depressed people to detect patterns.
“The model sees sequences of words or speaking style, and determines that these patterns are more likely to be seen in people who are depressed or not depressed,” Alhanai said. “Then, if it sees the same sequences in new subjects, it can predict if they’re depressed too.”
The model exhibited a 77 percent success rate in tests.
“If the model sees changes maybe it will be a flag to the doctors,” said co-researcher James Glass.
The app could be integrated into mobile apps that monitor a user’s voice and text. The team hopes to test additional data from subjects with other cognitive conditions, such as dementia.
“It’s not so much detecting depression, but it’s a similar concept of evaluating, from an everyday signal in speech, if someone has cognitive impairment or not,” Alhanai said.