Designing Software for Clinical Environments

Abstract

Intensive care units (ICUs) are complex and busy healthcare environments in which critically ill patients receive a wide range of clinical support, including medication, continuous observations and frequently multiple organ support. The heavily instrumented nature of these environments generates large volumes of data which is aggregated in clinical information systems and exposed to intensive care personnel using a variety of software tools which persist, organise and visualise the data to inform their decisions and allow them to adequately care for their patients. Furthermore, the data-intensive nature of the ICUs provides tremendous opportunities for advanced computing solutions, including data analytics and machine learning which can improve the efficiency of clinical staff and lead to better patient outcomes.
The constant advances in the field of informatics have brought on a period of rapid growth in research applying those technologies to healthcare settings. Despite this, the software developed for ICUs rarely incorporates the clinical staff in the design process which frequently leads to solutions that fail to satisfy all the end-user requirements. This thesis investigates the feasibility and identifies the challenges and opportunities in collaborative software design within clinical settings by presenting two distinct studies. It begins by disseminating and translating the current practices in collaborative intervention development for the process of software development in a hospital environment. These learnings are then applied in a practical setting to (1) construct and evaluate an intensive care dashboard for the management of COVID-19 patients amidst the global pandemic and (2) develop data annotation software which could enhance existing clinical datasets and pave the way for future machine learning applications within the intensive care. The presented findings strongly suggest the feasibility and benefits of collaborative design methods for software development within clinical settings and highlight the challenges and limitations associated with collaborating with intensive care staff.

Date of Award	4 Feb 2025
Original language	English
Awarding Institution	University of Bristol
Supervisor	Raul Santos-Rodriguez (Supervisor), Christopher Bourdeaux (Supervisor) & Chris J McWilliams (Supervisor)