The new artificial intelligence program can distinguish between people who are not affected or affected by one of the disorders, and it can also correctly distinguish between cases of depression and schizophrenia, as well as the degree to which the patient is currently affected by the disease.
The researchers provided a composite image representing the control group of their tests (left in the image below) and patients with mental disorders (right). The identities of several people are mixed during the testing period to assess the effectiveness of the program.
Doctors say that emotionally disturbed individuals tend to have raised eyebrows, sharp looks, and swollen faces, lips or drooping cheeks. To protect patient privacy, these emojis were made available to support the idea of the program.
The study was published under the name "The Face of Affective Disorders", and 8 researchers from a wide range of institutions from the private and public medical research sector participated in the experiments, and was published on the website of the Department of Computer Research and Recognition Models at Cornell University in the United States.
So far, AI has been used to identify the impact of these mainly facial abnormalities as a potential primary diagnostic tool. The new approach also provides an easy-to-follow method for assessing patients' progress during treatment, or in their local environment to monitor changes in them.
The researchers called this technology "Opto Electronic Encephalography", which is a method in which a doctor or specialist does not communicate directly with the patient, but rather the mental state is inferred by analyzing the image of the face instead of local sensors or medical imaging techniques based on radiation .
Data were collected from 100 patients of both sexes at the University Hospital in Aachen, along with a standard control group of 50 healthy subjects. Among the patients, 35 had schizophrenia and 65 had depression.