Hosted by the Interactive AI Centre for Doctoral Training
Abstract: Hypotension during perioperative care, if undetected or uncontrolled, can lead to serious clinical complications. Predictive machine learning models, based on routinely collected EHR data, offer potential for early warning of hypotension to enable proactive clinical intervention. However, while research has demonstrated the feasibility of such machine learning models, these often adopt a data-centric perspective and give less attention to grounding their formulation and development in socio-technical context of perioperative care work. In this talk I will discuss some research in which contextual understanding of the collaborative work practices of perioperative clinical teams is used to inform the development of hypotension predictive models for perioperative care. By appropriately situating models in the perioperative care workflow, there is potential to reconfigure care and facilitate more proactive and collaborative management of hypotension.
Please contact the Interactive AI CDT Admin Mailbox <iai-cdt@bristol.ac.uk> if you would like lunch; there will be food and the chance to network with colleagues from 1:30, followed by the talk from 2- 3pm.