USING BIG DATA IN CRITICAL CARE ACROSS TO IMPROVE CLINICAL OUTCOMES 1
Research type
Research Study
Full title
USING DATA IN CRITICAL CARE ACROSS ALL AGES TO IMPROVE CLINICAL OUTCOMES: THE UDICC STUDY
IRAS ID
270132
Contact name
Elias Pimenidis
Contact email
Sponsor organisation
University of West of England
Clinicaltrials.gov Identifier
N/A, N/A
Duration of Study in the UK
0 years, 11 months, 31 days
Research summary
Critical care Units (CCUs) are where the sickest patients are admitted and where large amounts of detailed clinical data are collected (usually hourly) for the duration of the patient’s stay. UHB, like many CCUs, has moved from paper to clinical information systems to capture data from the patients’ monitor, ventilator and other equipment into an extensive database. Currently, CCUs are not using these systems and data to their advantage, with much of the captured data left unanalysed. In an era of limited NHS resources, these digital resources have the potential to both optimise patient outcomes and make systems more efficient and effective.
Data analysis and machine learning Artificial Intelligence (AI) systems have been have been used widely in CCUs, primarily to automate processes where problems are well known and fully defined, and there the deliverables to efficiency and accuracy achieved are well within the expected levels [1,2]. In this project, the potential benefits of utilising the data generated by the CCU’s information system are not fully known, but the availability of such rich data, as is the case here, is a rare and potentially rewarding opportunity. This project contributes to CCU objectives, while also validating and advancing state-of-the-art tools in Computer Science.
CCUs aim to optimise the patients’ survival, clinical outcomes and to reduce harm caused by therapies. All CCUs have recognised targets to improve outcomes, such as maintaining an optimal sedation level, maintaining lung volumes delivered by the ventilator within a specific range and delivering a minimum amount of nutrition to patients whilst they are critically ill. Yet, these targets are often not achieved. This study aims to use these common targets to assess the feasibility of using this clinical data routinely collected can be used to improve the achievement of these targets.REC name
London - Bloomsbury Research Ethics Committee
REC reference
20/LO/0109
Date of REC Opinion
3 Feb 2020
REC opinion
Favourable Opinion