eSSENCE@LU 7:5 - Developing person-centred computational language assessments for diagnosing depression and anxiety

Psychiatric disorders are increasing. More than 300 million individuals suffer from depression globally and at its worst depression may lead to suicide. More efficient methods to early discover and monitor psychiatric disorders are needed to provide proper healthcare. To assess the state of mind of a patient in an interview, questions with numerical scales are often used, but we do not normally use numbers to tell others how we feel. We use words and language constructs, which carry much richer information.

This project develops a method to improve precision of diagnosing Major Depressive Disorder and Generalized Anxiety Disorder using artificial intelligence (AI) to analyse open-ended text responses in a computational language assessment.