[The role of artificial intelligence in psychiatry].

In recent decades a global problem in mental health has been the increase in the relative proportion of patients who do not receive care, which is associated with loss of life years and deterioration in quality of life. The practical application of artificial intelligence (AI) can help in the fields of data analysis, diagnosis, therapy planning, among others in psychiatric care, thus reducing the human resource input. Today's artificial narrow intelligence (ANI), also known as weak AI, can recognise patterns and correlations in large data sets with the help of machine learning procedures and to make autonomous decisions while making its own refinements. The use of AI-based systems may be effective in the classification of mental health disorders, in disease prevention, in clinical diagnosis and treatment without human input, and finally, it can play a supporting role in many areas of data analysis (quality care assessment, research). A key area of diagnostics is the estimation of suicidal risk and the assessment of mood status using machine learning, which can be used to make predictions with high accuracy, by analysing written text or speech. By examining correlations within large data sets, advances in precision medicine could also be made, allowing more accurate prediction of medication. Psychotherapeutic programs using artificial intelligence are already available today, which can provide users with easily accessible help, mainly using cognitive therapy tools. In addition to its obvious benefits, the use of artificial intelligence also raises ethical and methodological questions, making its regulation a key issue for the future.

The applicability of the Beck Depression Inventory and Hamilton Depression Scale in the automatic recognition of depression based on speech signal processing.

Depression is a growing problem worldwide, impacting on an increasing number of patients, and also affecting health systems and the global economy. The most common diagnostical rating scales of depression are self-reported or clinician-administered, which differ in the symptoms that they are sampling. Speech is a promising biomarker in the diagnostical assessment of depression, due to non-invasiveness and cost and time efficiency. In our study, we try to achieve a more accurate, sensitive model for determining depression based on speech processing. Regression and classification models were also developed using a machine learning method. During the research, we had access to a large speech database that includes speech samples from depressed and healthy subjects. The database contains the Beck Depression Inventory (BDI) score of each subject and the Hamilton Rating Scale for Depression (HAMD) score of 20% of the subjects. This fact provided an opportunity to compare the usefulness of BDI and HAMD for training models of automatic recognition of depression based on speech signal processing. We found that the estimated values of the acoustic model trained on BDI scores are closer to HAMD assessment than to the BDI scores, and the partial application of HAMD scores instead of BDI scores in training improves the accuracy of automatic recognition of depression.

Reliability and validity of the Hungarian version of the Personality Inventory for DSM-5 (PID-5).

OBJECTIVES AND METHODS: In order to assess the internal consistency, fit indexes, test-retest reliability, and validity of the Personality Inventory for the DSM-5 (PID-5) and its associations with age, gender, and education, 471 non-clinical (69,6% female; mean age: 37,63) and 314 clinical participants (69,7% female, mean age: 37,41) were administered the Hungarian translation of the PID-5, as well as the SCL-90-R and the SCID-II Personality Questionnaire. RESULTS: We found that; (a) temporal consistency of the Hungarian PID-5 was confirmed by one-month test-retest reliability analysis, (b) validity of the PID-5 instrument is acceptable in the clinical and the non-clinical sample as well, based on significant correlations with SCID-II and SCL-90-R, (c) PID-5 facets' and domains' associations with gender, age, and level of education are in accordance with previous findings. CONCLUSION: These findings support that the Hungarian PID-5 is a reliable and valid instrument for both clinical and non-clinical populations.