Depression certainly has its symptoms and indicators, but what if there was a more advanced way to identify it? Over as the esteemed Massachusetts college MIT, researchers have been testing an artificial intelligence system that may be able to flag warning signs based on the way that we communicate.
This groundbreaking research actually analyzes speech and text messages to see if certain patterns appear that may indicate depression. Incorporating the use of a neural network model; the A.I. listens to (or reads) conversations, then provides a diagnosis. Interestingly, no direct questions or answers are necessary. For this to work, people just need to carry out regular conversations.
“We call it ‘context-free’ because you’re not putting any constraints into the types of questions you’re looking for and the type of responses to those questions,” MIT analyst Tuka Alhanai explained. “If you want to deploy [depression-detection] models in a 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.”
Trigger points that may lead to a depression diagnosis include longer pauses between words or a slower pattern of speech. When it comes to texting, words like “low,” “sad” or “down” raise the red flags. Patterns are sought out as well, indicating that these types of behaviors happen regularly when a particular person is having a long dialogue.
“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 added. “Then, if it sees the same sequences in new subjects, it can predict if they’re depressed too.”
Though it’s still in the testing phase, Alhanai has high hopes for making these A.I. programs more available. He did not rule out the possibility of turning this tool into a Smartphone app that can be used for voice recordings and alerts. He also foresees doctors and counselors using it for their own professional assessments.
One other interesting stat mentioned in the article was the fact that 37 percent of people suffering from depression in the U.S. continue to go undiagnosed. And as we all know, these types of dark feelings can be a gateway to addiction, self-harm or even suicide. Let’s hope this future tech can decrease that number.