Researchers from the Computational Science and Artificial Intelligence Laboratory (CSAIL) of the Massachusetts Institute of Technology (MIT) have developed a neural network that allows to determine the level of depression of a patient. Artificial intelligence is able to establish an oppressed psychological state, without relying on context and without asking specific questions. To obtain the test result, it is enough to record a patient interview in video or audio format.
By training the neural network, CSAIL scientists used 142 interview records from the Distress Analysis Interview Corpus, a compilation intended for the diagnosis of mental illness. Artificial intelligence analyzed speech of patients, revealing sound and text patterns. Patterns have become, including word-markers, such as "sad", "low", combined with long pauses and a monotonous voice. The oppressed condition of each patient was assessed on a scale from 0 to 27. Depression was considered to be a level of 15 and above.
In subsequent testing, artificial intelligence managed to recognize depression in 77% of cases. According to the developers, this result is one of the best among all available.
The new technology is considered as a tool that allows to simplify the work of the therapist and specify certain markers, which should be noted in the diagnosis.