Understanding and applying practitioner and patient views on the implementation of a novel automated Computer-Aided Risk Score (CARS) predicting the risk of death following emergency medical admission to hospital: qualitative study

Abstract

ObjectivesThe Computer-Aided Risk Score (CARS) estimates the risk of death following emergency admission to medical wards using routinely collected vital signs and blood test data. Our aim was to elicit the views of healthcare practitioners (staff) and service users and carers (SU/C) on (1) the potential value, unintended consequences and concerns associated with CARS and practitioner views on (2) the issues to consider before embedding CARS into routine practice.SettingThis study was conducted in two National Health Service (NHS) hospital trusts in the North of England. Both had in-house information technology (IT) development teams, mature IT infrastructure with electronic National Early Warning Score (NEWS) and were capable of integrating NEWS with blood test results. The study focused on emergency medical and elderly admissions units. There were 60 and 39 acute medical/elderly admissions beds at the two NHS hospital trusts.ParticipantsWe conducted eight focus groups with 45 healthcare practitioners and two with 11 SU/Cs in two NHS acute hospitals.ResultsStaff and SU/Cs recognised the potential of CARS but were clear that the score should not replace or undermine clinical judgments. Staff recognised that CARS could enhance clinical decision-making/judgments and aid communication with patients. They wanted to understand the components of CARS and be reassured about its accuracy but were concerned about the impact on intensive care and blood tests.ConclusionRisk scores are widely used in healthcare, but their development and implementation do not usually involve input from practitioners and SU/Cs. We contributed to the development of CARS by eliciting views of staff and SU/Cs who provided important, often complex, insights to support the development and implementation of CARS to ensure successful implementation in routine clinical practice.

Ensuring patient and public involvement in the transition to AI‐assisted mental health care: A systematic scoping review and agenda for design justice

“…Despite the advantages of efficiency of scale and depth of computational power, 3 , 4 , 5 concerns have been expressed by scientists, practitioners and broader publics about the systematic datafication of people's lives and their lived experiences of health and illness. 6 , 7 , 8 , 9 , 10 It is unclear whether AI‐assisted health care always leads to better patient outcomes, whether it empowers and enables patients/service users, carers and their families, and whether patients or the public have a meaningful say over AI‐assisted processes of care or design of such systems. 11 , 12 , 13 …”

Implementation and clinical utility of a Computer-Aided Risk Score for Mortality (CARM): a qualitative study

“…Our approach to the development of CARM has involved a process of codesign with healthcare professionals and service users 6. Previous papers discuss the development and validation2 and the potential value, unintended consequences, concerns and predicted implementation needs6 of the CARM.…”

“…We have sought to codesign CARM with service users and carers as part of the project team as well as participants 6 9. In the study reported here, we had the input of three team members (GB, KD and JG) from the Service User and Carer Involvement in Research Group at the University of Bradford, which has been involved in the development of CARM over the last 4 years.…”

“…Uniquely, concurrent to the statistical development of CARM, healthcare practitioners, service users and carers contributed to the development of the score to establish views on the potential value, unintended consequences, concerns and implementation needs of the score 6. Health technologies, such as risk scores, may falter due to poor implementation practices, poorly designed usability features and other contextual factors 6.…”

Patient similarity analytics for explainable clinical risk prediction

“…Given that different doctors and patients have unique preferences for the type and style of information delivery, patient similarity models will probably not replace conventional risk models, but complement them with a new variety of information that can be selectively used in the appropriate consultation context. [28].…”