16 December 2022 – 08:28
Our thoughts determine how we feel and behave. Understanding certain mindsets is an important part of the prevention and treatment of depression. Delft researcher Franziska Burger investigated how AI can support people with symptoms of depression. She developed a computer program that analyzes thought records with natural language processing and recognizes underlying patterns. This gives people with depressive symptoms better and faster insight into negative thoughts. Burger’s research contributes to the use of AI technology in the development of software for the prevention and treatment of depressive symptoms. Today, Burger defended his thesis ‘Supporting Electronic Mental Health for Depression with Artificial Intelligence’ at TU Delft.
Burger’s research shows that AI can very effectively identify core thoughts in depressed people, such as ‘I’m not competent’, ‘I’m worthless’ and ‘I’m not loved’. For this, she trained AI to recognize the underlying idea with structured, short texts. For example, consider the combination of ‘I’m not loved’ with the core belief ‘My partner doesn’t like me because he ignores me when I wave enthusiastically at him’. Understanding these unhelpful thoughts is a first step in cognitive therapy – only by recognizing them can you begin to replace them with healthier thoughts. Unfortunately, depressed people are often unable to identify these unhelpful thoughts, but AI could support this.
Although the potential is obvious, Burger found that interactivity between user and computer systems for depression treatment is limited to date. She bases this on an extensive study of the scientific literature from 2000 to 2017. The research showed that in existing systems the user is asked to provide information, but the systems do so little about it. This set her on the path to using AI to analyze the rich text data in a substantive way. Burger focused on a subclinical target group. This group can serve as the basis for a possible follow-up examination for people with diagnosed depression. She hopes developers will incorporate her AI technology into their treatment or prevention systems in the future.
Franziska Burger: “As a person, you want the system to understand your content. With our research, we have now taken a step in that direction. We saw that people were very capable of discovering their core thoughts with a smart chat program.”
Read more here: Supporting electronic mental health with artificial intelligence | TU Delft Repositories
Source: Delft University of Technology