Acquisition and Analysis of Relationships Between Longitudinal Emotional Signals Produced by an Artificial Intelligence Algorithm and Self-questionnaires Used in the Psychiatric Follow-up of Patients With Mood and/or Anxiety Disorders: a Real-Environment Study.

The worldwide prevalence of anxiety and depression increased massively during the pandemic, with a 25% rise in the number of patients suffering from psychological distress. Psychiatrists, and even more so general practitioners, need measurement tools that enable them to remotely monitor their patients' psychological state of health, and to be automatically alerted in the event of a break in behavior. In this study, the investigators propose to collect clinical data along with longitudinal measurement of patients' emotions. Emobot proposes to analyze the evolution of mood disorders over time by passively studying people's emotional behavior. The aim of EMOACQ-1 is to acquire knowledge and produce a quantitative link between emotional expression and mood disorders, ultimately facilitating the understanding and management of these disorders. Through this study, could be developed a technological solution to support healthcare professionals and patients in psychiatry, a field known as the "poor relation of medicine" and lacking in resources. Such a solution would enable better understanding, disorders remote \& continuous monitoring and, ultimately, better treatment of these disorders. The investigators will process the data by carrying out a number of analyses, including descriptive, comparative and correlation studies of the data from the self-questionnaire results and the emotional signals captured by the devices. Finally, the aim will be to predict questionnaire scores from the emotional signals produced.