Accepted for/Published in: JMIR Research Protocols
Date Submitted: Jan 27, 2021
Date Accepted: Jun 3, 2021
Predicting and responding to clinical deterioration in hospitalized patients using artificial intelligence by physician-nurse clinical teams: SEIPS-based protocol for a mixed method stepped-wedge design
ABSTRACT
Background:
Early identification of clinical deterioration in patients on hospital units can decrease mortality and improve other patient outcomes, yet remains a challenge in busy hospital settings. Artificial intelligence (AI) in the form of predictive models are increasingly being explored for their potential to assist clinicians with predicting clinical deterioration.
Objective:
This study aims to assess the impact of an AI-enabled work system that was built around a “clinical deterioration index” (CDI) predictive model on clinical outcomes and explore how the incorporation of AI affects the work system to mediate these outcomes using the Systems Engineering Initiative for Patient Safety (SEIPS) 2.0 model.
Methods:
This study will employ a mixed method approach informed by the SEIPS 2.0 model to assess both processes and outcomes with a focus on how physician-nurse clinical teams are affected by the presence of AI. The intervention will be implemented in hospital medicine units based on a modified stepped-wedge design featuring three stages over 11 months: stage 0 represents a baseline period 10 months prior to implementation of the intervention; stage 1 introduces the CDI predictions to physicians only and triggers a physician-driven workflow; stage 2 introduces the CDI predictions to the entire multidisciplinary team that includes both physicians and nurses and triggers a nursing-driven workflow. Quantitative data will be collected from the EHR on clinical processes and outcomes. Interviews will be conducted with members of the multidisciplinary team to understand how the intervention changes the existing work system and processes. The SEIPS 2.0 model will provide an analytic framework for a mixed method analysis.
Results:
A pilot period for the study began in December 2020; results are expected in mid-2022.
Conclusions:
This protocol paper proposes an approach to evaluation which recognizes the importance of assessing both processes and outcomes to understand how a multifaceted AI-enabled intervention affects the complex team-based work of identifying and managing clinical deterioration.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.