학술논문

2238 When a doctor and a nurse share their view in a simulated emergency care interaction: developing an automatic gaze annotation method for multiple eye-tracking data analysis
Document Type
Article
Source
Emergency Medicine Journal; 2023, Vol. 40 Issue: 12 p881-882, 2p
Subject
Language
ISSN
14720205; 14720213
Abstract
Aims and ObjectivesCollective competence of a healthcare team is key to patient safety and quality in healthcare. This presentation reports part of a UK-Japan interdisciplinary research project on emergency care team interactions, focusing on gaze behaviour. The study investigates how healthcare professionals achieve joint attention for joint action. To describe the complex practice, we are developing a programme to automatically annotate multiple gaze data. Method and DesignFor a pilot study, a small-scale simulation session was filmed in a large teaching hospital in the UK with two pairs of eye-tracking glasses (Tobii Pro Glasses 2) worn by an ED consultant and an ED nurse. The scenario was a collapse in a ward, which involved two simulated patients, one acting as a female patient aged 72 and the other as her sister. Video images of the first three minutes of the recording were extracted from two eye-trackers, and the moments when a doctor and a nurse shared a field of view were automatically annotated by utilizing the feature point detection technology. Results and ConclusionThree forms of joint gaze behaviours were recognised: joint attention (two people look at the same part of an object), narrow joint field view (two people look at different parts of an object, see figure 1), and broad joint field view (two people share a view field but look at different objects). Although it is still preliminary, the technology enables researchers to analyse shared field view, in addition to joint attention, between team members. This has great potential for further research on health team interactions and its application to medical education.[Figure]