Embodied Conversational Agents (ECAs) are promising software to communicate with patients but no study has tested them in the diagnostic field of mental disorders. The aim of this study was 1) to test the performance of a diagnostic system for major depressive disorders (MDD), based on the identification by an ECA of specific symptoms (the MDD DSM 5 criteria) in outpatients; 2) to evaluate the acceptability of such an ECA. Patients completed two clinical interviews in a randomized order (ECA versus psychiatrist) and filled in the Acceptability E-scale (AES) to quantify the acceptability of the ECA. 179 outpatients were included in this study (mean age 46.5 ± 12.9 years, 57.5% females). Among the 35 patients diagnosed with MDD by the psychiatrist, 14 (40%) patients exhibited mild, 12 (34.3%) moderate and 9 (25.7%) severe depressive symptoms. Sensitivity increased across the severity level of depressive symptoms and reached 73% for patients with severe depressive symptoms, while specificity remained above 95% for all three severity levels. The acceptability of the ECA evaluated by the AES was very good (25.4). We demonstrate here the validity and acceptability of an ECA to diagnose major depressive disorders. ECAs are promising tools to conduct standardized and well-accepted clinical interviews.

International audienc

Virtual agents have demonstrated their ability to conduct clinical interviews. However, the factors influencing patients' engagement with these agents have not yet been assessed. The objective of this study is to assess in outpatients the trust and acceptance of virtual agents performing medical interviews and to explore their influence on outpatients' engagement. In all, 318 outpatients were enroled. The agent was perceived as trustworthy and well accepted by the patients, confirming the good engagement of patients in the interaction. Older and less-educated patients accepted the virtual medical agent (VMA) more than younger and welleducated ones. Credibility of the agent appeared to main dimension, enabling engaged and non-engaged outpatients to be classified. Our results show a high rate of engagement with the virtual agent that was mainly related to high trust and acceptance of the agent. These results open new paths for the future use of VMAs in medicine.npj Digital Medicine (2020) 3:2 ; https://doi.