The way doctors deliver bad news has a significant impact on the therapeutic process. In order to facilitate doctor’s training, we have developed an embodied conversational agent simulating a patient to train doctors to break bad news. In this article, we present an evaluation of the virtual reality training platform comparing the users’ experience depending on the virtual environment displays: a PC desktop, a virtual reality headset, and four wall fully immersive systems. The results of the experience, including both real doctors and naive participants, reveal a significant impact of the environment display on the perception of the user (sense of presence, sense of co-presence, perception of the believability of the virtual patient), showing, moreover, the different perceptions of the participants depending on their level of expertise.

In this paper, we introduce a two-step corpora-based methodology, starting from a corpus of human-human interactions to construct a semi-autonomous system in order to collect a new corpus of human-machine interaction, a step before the development of a fully autonomous system constructed based on the analysis of the collected corpora. The presented methodology is illustrated in the context of a virtual reality training platform for doctors breaking bad news.

À travers notre étude, nous proposons une analyse linguistique des interactions patient/médecin en situation de formation à l'annonce d'événement indésirable grave (EIG). Nous nous plaçons dans le cadre de la linguistique interactionnelle, laquelle a pour objectif d'étudier les structures et les usages de la langue, en interaction et dans son environnement naturel (Selting et Couper-Kuhlen, 2001 : 1). Nous adoptons également une perspective multimodale, à savoir que nous considérons la parole comme un tout composé de vocalisations, de gesticulations, d'expressions faciales, etc. (McNeill, 1992). Partant du constat de Lausberg et Sloetjes (2009) selon lequel la méthodologie employée pour la catégorisation gestuelle, notamment, n'est souvent pas clairement définie et reste opaque, nous souhaitons exposer le schéma d'annotation utilisé dans notre étude de façon claire et précise. Ce schéma s'articule autour de deux notions interactionnelles que sont les séquences de réparation et les feedbacks et des différentes modalités langagières.

The paper aims at presenting the Acorformed corpus composed of human-human and human-machine interactions in French in the specific context of training doctors to break bad news to patients. In the context of human-human interaction, an audiovisual corpus of interactions between doctors and actors playing the role of patients during real training sessions in French medical institutions have been collected and annotated. This corpus has been exploited to develop a platform to train doctors to break bad news with a virtual patient. The platform has been exploited to collect a corpus of human-virtual patient interactions annotated semi-automatically and collected in different virtual reality environments with different degree of immersion (PC, virtual reality headset and virtual reality room).

Ropivacaine continuous wound infusions (CWIs) are extensively used as a component of multimodal analgesia. The rational application of CWI of ropivacaine requires a thorough understanding of its pharmacokinetics to investigate the risk of potential systemic toxicity. A population pharmacokinetic (popPK) study was undertaken to describe the pharmacokinetics of ropivacaine CWI during 75 hours. Women undergoing a unilateral mastectomy were scheduled to receive CWI for 40 hours for postoperative analgesia. A 10‐mL ropivacaine 0.75% bolus followed by continuous infusion (400 mL of 0.2% ropivacaine at a flow rate of 10 mL/h) was administered via a multihole catheter placed on the major pectoral muscle. PopPK analysis was performed using the nonlinear mixed‐effects model. A 1‐compartment disposition model with an absorption compartment and a transit compartment for the infusion best describes the data (67 observations from 10 women). Population parameter estimates (between‐subject variability, %) are apparent central volume (V/F) 269 L (39.1%), apparent clearance (CL/F) 18.8 h ‐1 (74.9%), and absorption rate (K12) 0.406 h ‐1 . The model predicted C max as 1.45 ± 0.80 μg/mL, which occurred in the 42.4 th hour (39–45.9 hours). This popPK model describes the pharmacokinetics of ropivacaine during continuous wound infusion and confirms the safety profile of the present technique.

The way doctors deliver bad news has a significant impact on the therapeutic process. In this paper, we present an ongoing project that aim at developing an embodied conversational agent simulating a patient to train doctors to break bad news. The embodied conversational agent is incorporated in an immersive virtual reality environment integrating several sensors to detect and recognize in real time the verbal and non-verbal behavior of the doctors interacting with the virtual patient. The virtual patient behavior as well as the virtual environment are constructed based on a methodology mixing a corpus-based approach, real medical data and expertise and empirical and theoretical studies on human-machine interaction.