Depression is not straightforward to diagnose and medical professionals seek to do so by asking patients specific questions about their mood, mental illness, lifestyle and personal history. The collected information is then used to arrive at a diagnosis. Finding new ways to assess depression is of interest to medical science. Worldwide, over 350 million people have depression according to the World Health Organization, and rates are said to be climbing.
A number of projects are using the basis of computational neuroscience to develop artificer intelligence solutions for assessing depression. One such project is based at the Massachusetts Institute of Technology. The basis is set out by lead researcher Tuka Alhanai, who tells Engagdet: “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. 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.”
To develop the artificial intelligence, the research group used data relating to 142 individuals undergoing depression. They screened and modeled the interactions with audio and text features in a Long-Short Term Memory neural network model to detect depression. The experimental results were comparable to methods that explicitly modeled the topics of the questions and answers which suggests that depression can be detected through sequential modeling of an interaction. This sets the basis for further study.
In related news, scientists based at Harvard and the University of Vermont have developed a means to use Instagram to assess rates of depression. By applying machine learning tools, the researchers constructed a model that can predict whether a person is clinically depressed. The results are reported to have a high level of accuracy.
It might even be possible for artificial intelligence systems to be come ‘depressed’, according to neuroscientist Zachary Mainen. Writing in The Guardian, Mainen speculates: “Imagine a robot with a hardware malfunction. Perhaps it needs to learn a new way of grasping information. If its learning rate is not high enough, it may lack the flexibility to change its algorithms. If severely damaged, it might even need to adopt new goals. If it fails to adapt it could give up and stop trying.”