Virtual human as a new diagnostic tool, a proof of concept study in the field of major depressive disorders

Pierre Philip, Jean-Arthur Micoulaud-Franchi, Patricia Sagaspe, Etienne De Sevin, Jérôme Olive, Stéphanie Bioulac, Alain Sauteraud
Sci Rep. 2017-02-16; 7(1):
DOI: 10.1038/srep42656

Lire sur PubMed

1. Sci Rep. 2017 Feb 16;7:42656. doi: 10.1038/srep42656.

Virtual human as a new diagnostic tool, a proof of concept study in the field of
major depressive disorders.

Philip P(1)(2)(3), Micoulaud-Franchi JA(1)(2)(3), Sagaspe P(1)(2)(3), Sevin
E(2)(3), Olive J(2)(3), Bioulac S(2)(3)(4), Sauteraud A(2)(3).

Author information:
(1)Clinique du Sommeil, Service d’Explorations Fonctionnelles du Système Nerveux,
CHU de Bordeaux, Place Amélie Raba-Léon, 33076 Bordeaux, France.
(2)Univ. Bordeaux, SANPSY, USR 3413, F-33000 Bordeaux, France.
(3)CNRS, SANPSY, USR 3413, F-33000 Bordeaux, France.
(4)Pôle Universitaire Psychiatrie Enfants et Adolescents, Centre Hospitalier
Charles Perrens, 121, rue de la Béchade, 33076 Bordeaux, France.

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.

DOI: 10.1038/srep42656
PMCID: PMC5311989
PMID: 28205601

Auteurs Bordeaux Neurocampus