Now, researchers at MIT’s Computer Science and Artificial Intelligence Laboratory are working on an algorithm<\/a> that could eliminate some of that guesswork. They used text and audio data from 142 interviews with patients — 30 of whom had been diagnosed with depression — to teach a machine learning algorithm<\/a> to listen for signs of depression in speech.<\/p> What makes this effort stand out is that the researchers examined the patients’ tone of voice, not just the specific words they used. That technique made the model surprisingly accurate: It was able to identify subjects who had been diagnosed with depression with a 77 percent success rate.<\/p> But before we go on and implement AI as a tool to diagnose mental disorders in the real world, we’ll have to take these results with a substantial grain of salt.<\/p> While chatbots like Woebot<\/a> have recently surfaced help people to deal with depression, they won’t be able to replace a human therapist, at least for the time being.<\/p> There are far too many variables, and while 77 percent sounds promising, a false positive could raise serious ethical concerns. For instance, AI diagnostic tools could fall into the wrong hands — like your employer or insurance company.<\/p> But the researchers are realistic about their machine learning model’s ability to detect depression. Rather than replacing human therapists, they see it as another tool in [a clinician’s] toolbox,” MIT researcher James Glass, who worked on the model, told<\/a> Smithsonian<\/em>.<\/p> READ MORE<\/strong>: Can Artificial Intelligence Detect Depression in a Person’s Voice?<\/a> [Smithsonian<\/em>]<\/p> More on treating depression<\/strong>: New App for Depression Uses Artificial Intelligence for Therapy Treatments<\/a><\/p> View original post here: Diagnosing\u00a0Depression Depression can manifest with\u00a0 many different symptoms , from a \u201closs of energy\u201d to \u201cindecisiveness\u201d\u00a0\u2014\u00a0broad criteria that\u00a0make the condition difficult\u00a0to diagnose with a high degree of certainty. Now, researchers at\u00a0MIT\u2019s Computer Science and Artificial Intelligence Laboratory\u00a0 are working on an algorithm \u00a0that could eliminate some of that guesswork.\u00a0They used text and audio data from 142 interviews with patients \u2014 30 of whom had been diagnosed with depression \u2014\u00a0to teach a\u00a0 machine learning algorithm \u00a0to listen for signs of depression in speech. Continue reading Tone of Voice<\/h2>
AI Therapy<\/h2>
![](\"https:\/\/wp-assets.futurism.com\/2018\/11\/ai-depressed-listening-talk-1200x630.png\")
<\/p>
AI Can Tell If You’re Depressed by Listening to You Talk<\/a><\/p>","protected":false},"excerpt":{"rendered":"