Predicting and Responding to Clinical Deterioration in Hospitalized Patients by Using Artificial Intelligence: Protocol for a Mixed Methods, Stepped Wedge Study

Using Theories, Models, and Frameworks to Inform Implementation Cycles of Computerized Clinical Decision Support Systems in Tertiary Health Care Settings: Scoping Review

BACKGROUND

Computerized clinical decision support systems (CDSSs) are essential components of modern health system service delivery, particularly within acute care settings such as hospitals. Theories, models, and frameworks may assist in facilitating the implementation processes associated with CDSS innovation and its use within these care settings. These processes include context assessments to identify key determinants, implementation plans for adoption, promoting ongoing uptake, adherence, and long-term evaluation. However, there has been no prior review synthesizing the literature regarding the theories, models, and frameworks that have informed the implementation and adoption of CDSSs within hospitals.

OBJECTIVE

This scoping review aims to identify the theory, model, and framework approaches that have been used to facilitate the implementation and adoption of CDSSs in tertiary health care settings, including hospitals. The rationales reported for selecting these approaches, including the limitations and strengths, are described.

METHODS

A total of 5 electronic databases were searched (CINAHL via EBSCOhost, PubMed, Scopus, PsycINFO, and Embase) to identify studies that implemented or adopted a CDSS in a tertiary health care setting using an implementation theory, model, or framework. No date or language limits were applied. A narrative synthesis was conducted using full-text publications and abstracts. Implementation phases were classified according to the "Active Implementation Framework stages": exploration (feasibility and organizational readiness), installation (organizational preparation), initial implementation (initiating implementation, ie, training), full implementation (sustainment), and nontranslational effectiveness studies.

RESULTS

A total of 81 records (42 full text and 39 abstracts) were included. Full-text studies and abstracts are reported separately. For full-text studies, models (18/42, 43%), followed by determinants frameworks (14/42,33%), were most frequently used to guide adoption and evaluation strategies. Most studies (36/42, 86%) did not list the limitations associated with applying a specific theory, model, or framework.

CONCLUSIONS

Models and related quality improvement methods were most frequently used to inform CDSS adoption. Models were not typically combined with each other or with theory to inform full-cycle implementation strategies. The findings highlight a gap in the application of implementation methods including theories, models, and frameworks to facilitate full-cycle implementation strategies for hospital CDSSs.

Multicenter study of racial and ethnic inequities in liver transplantation evaluation: Understanding mechanisms and identifying solutions

Racial and ethnic disparities persist in access to the liver transplantation (LT) waiting list; however, there is limited knowledge about underlying system-level factors that may be responsible for these disparities. Given the complex nature of LT candidate evaluation, a human factors and systems engineering approach may provide insights. We recruited participants from the LT teams (coordinators, advanced practice providers, physicians, social workers, dieticians, pharmacists, leadership) at two major LT centers. From December 2020 to July 2021, we performed ethnographic observations (participant-patient appointments, committee meetings) and semistructured interviews (N = 54 interviews, 49 observation hours). Based on findings from this multicenter, multimethod qualitative study combined with the Systems Engineering Initiative for Patient Safety 2.0 (a human factors and systems engineering model for health care), we created a conceptual framework describing how transplant work system characteristics and other external factors may improve equity in the LT evaluation process. Participant perceptions about listing disparities described external factors (e.g., structural racism, ambiguous national guidelines, national quality metrics) that permeate the LT evaluation process. Mechanisms identified included minimal transplant team diversity, implicit bias, and interpersonal racism. A lack of resources was a common theme, such as social workers, transportation assistance, non-English-language materials, and time (e.g., more time for education for patients with health literacy concerns). Because of the minimal data collection or center feedback about disparities, participants felt uncomfortable with and unadaptable to unwanted outcomes, which perpetuate disparities. We proposed transplant center-level solutions (i.e., including but not limited to training of staff on health equity) to modifiable barriers in the clinical work system that could help patient navigation, reduce disparities, and improve access to care. Our findings call for an urgent need for transplant centers, national societies, and policy makers to focus efforts on improving equity (tailored, patient-centered resources) using the science of human factors and systems engineering.

Am I safe? An Interpretative Phenomenological Analysis of Vulnerability as Experienced by Patients With Complications Following Surgery

Abdominal surgery carries with it risks of complications. Little is known about patients' experiences of post-surgical deterioration. There is a real need to understand the psychosocial as well as the biological aspects of deterioration in order to improve care and outcomes for patients. Drawing on in-depth interviews with seven abdominal surgery survivors, we present an idiographic account of participants' experiences, situating their contribution to safety within their personal lived experiences and meaning-making of these episodes of deterioration. Our analysis reveals an overarching group experiential theme of vulnerability in relation to participants' experiences of complications after abdominal surgery. This encapsulates the uncertainty of the situation all the participants found themselves in, and the nature and seriousness of their health conditions. The extent of participants' vulnerability is revealed by detailing how they made sense of their experience, how they negotiated feelings of (un)safety drawing on their relationships with family and staff and the legacy of feelings they were left with when their expectations of care (care as imagined) did not meet the reality of their experiences (care as received). The participants' experiences highlight the power imbalance between patients and professionals in terms of whose knowledge counts within the hospital context. The study reveals the potential for epistemic injustice to arise when patients' concerns are ignored or dismissed. Our data has implications for designing strategies to enable escalation of care, both in terms of supporting staff to deliver compassionate care, and in strengthening patient and family involvement in rescue processes.

Moving nursing innovation to prime time through the use of creative partnerships

Nurses are well-positioned to solve many problems in healthcare through engagement in innovation. Support from healthcare organizations to facilitate creative partnerships may accelerate nurses' ability to innovate and improve job satisfaction. The value of creative partnerships is rooted in the diversity of experiences and skillsets of each project team member. While nurses may be content experts and key stakeholders, they often lack experience with project management, information technology, product development, and other important skills. We describe the use of co-creation approaches in creative partnerships with diverse stakeholders to enhance the ability of nurse-led project teams to build valuable and sustainable products or services.

Artificial Intelligence for the Prediction of In-Hospital Clinical Deterioration: A Systematic Review

To analyze the available literature on the performance of artificial intelligence-generated clinical models for the prediction of serious life-threatening events in non-ICU adult patients and evaluate their potential clinical usage.

Evaluating clinician‐led quality improvement initiatives: A system‐wide embedded research partnership at Stanford Medicine

Introduction

Many healthcare delivery systems have developed clinician‐led quality improvement (QI) initiatives but fewer have also developed in‐house evaluation units. Engagement between the two entities creates unique opportunities. Stanford Medicine funded a collaboration between their Improvement Capability Development Program (ICDP), which coordinates and incentivizes clinician‐led QI efforts, and the Evaluation Sciences Unit (ESU), a multidisciplinary group of embedded researchers with expertise in implementation and evaluation sciences.

Aim

To describe the ICDP‐ESU partnership and report key learnings from the first 2 y of operation September 2019 to August 2021.

Methods

Department‐level physician and operational QI leaders were offered an ESU consultation to workshop design, methods, and overall scope of their annual QI projects. A steering committee of high‐level stakeholders from operational, clinical, and research perspectives subsequently selected three projects for in‐depth partnered evaluation with the ESU based on evaluability, importance to the health system, and broader relevance. Selected project teams met regularly with the ESU to develop mixed methods evaluations informed by relevant implementation science frameworks, while aligning the evaluation approach with the clinical teams' QI goals.

Results

Sixty and 62 ICDP projects were initiated during the 2 cycles, respectively, across 18 departments, of which ESU consulted with 15 (83%). Within each annual cycle, evaluators made actionable, summative findings rapidly available to partners to inform ongoing improvement. Other reported benefits of the partnership included rapid adaptation to COVID‐19 needs, expanded clinician evaluation skills, external knowledge dissemination through scholarship, and health system‐wide knowledge exchange. Ongoing considerations for improving the collaboration included the need for multi‐year support to enable nimble response to dynamic health system needs and timely data access.

Conclusion

Presence of embedded evaluation partners in the enterprise‐wide QI program supported identification of analogous endeavors (eg, telemedicine adoption) and cross‐cutting lessons across QI efforts, clinician capacity building, and knowledge dissemination through scholarship.

Early Prediction of Multiple Organ Dysfunction in the Pediatric Intensive Care Unit

Objective: The objective of the study is to build models for early prediction of risk for developing multiple organ dysfunction (MOD) in pediatric intensive care unit (PICU) patients. Design: The design of the study is a retrospective observational cohort study. Setting: The setting of the study is at a single academic PICU at the Johns Hopkins Hospital, Baltimore, MD. Patients: The patients included in the study were <18 years of age admitted to the PICU between July 2014 and October 2015. Measurements and main results: Organ dysfunction labels were generated every minute from preceding 24-h time windows using the International Pediatric Sepsis Consensus Conference (IPSCC) and Proulx et al. MOD criteria. Early MOD prediction models were built using four machine learning methods: random forest, XGBoost, GLMBoost, and Lasso-GLM. An optimal threshold learned from training data was used to detect high-risk alert events (HRAs). The early prediction models from all methods achieved an area under the receiver operating characteristics curve ≥0.91 for both IPSCC and Proulx criteria. The best performance in terms of maximum F1-score was achieved with random forest (sensitivity: 0.72, positive predictive value: 0.70, F1-score: 0.71) and XGBoost (sensitivity: 0.8, positive predictive value: 0.81, F1-score: 0.81) for IPSCC and Proulx criteria, respectively. The median early warning time was 22.7 h for random forest and 37 h for XGBoost models for IPSCC and Proulx criteria, respectively. Applying spectral clustering on risk-score trajectories over 24 h following early warning provided a high-risk group with ≥0.93 positive predictive value. Conclusions: Early predictions from risk-based patient monitoring could provide more than 22 h of lead time for MOD onset, with ≥0.93 positive predictive value for a high-risk group identified pre-MOD.