Queensland Digital Health Clinical Charter: a clinical consensus statement on priorities for digital health in hospitals

Implementing AI in Hospitals to Achieve a Learning Health System: Systematic Review of Current Enablers and Barriers

BACKGROUND

Efforts are underway to capitalize on the computational power of the data collected in electronic medical records (EMRs) to achieve a learning health system (LHS). Artificial intelligence (AI) in health care has promised to improve clinical outcomes, and many researchers are developing AI algorithms on retrospective data sets. Integrating these algorithms with real-time EMR data is rare. There is a poor understanding of the current enablers and barriers to empower this shift from data set-based use to real-time implementation of AI in health systems. Exploring these factors holds promise for uncovering actionable insights toward the successful integration of AI into clinical workflows.

OBJECTIVE

The first objective was to conduct a systematic literature review to identify the evidence of enablers and barriers regarding the real-world implementation of AI in hospital settings. The second objective was to map the identified enablers and barriers to a 3-horizon framework to enable the successful digital health transformation of hospitals to achieve an LHS.

METHODS

The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines were adhered to. PubMed, Scopus, Web of Science, and IEEE Xplore were searched for studies published between January 2010 and January 2022. Articles with case studies and guidelines on the implementation of AI analytics in hospital settings using EMR data were included. We excluded studies conducted in primary and community care settings. Quality assessment of the identified papers was conducted using the Mixed Methods Appraisal Tool and ADAPTE frameworks. We coded evidence from the included studies that related to enablers of and barriers to AI implementation. The findings were mapped to the 3-horizon framework to provide a road map for hospitals to integrate AI analytics.

RESULTS

Of the 1247 studies screened, 26 (2.09%) met the inclusion criteria. In total, 65% (17/26) of the studies implemented AI analytics for enhancing the care of hospitalized patients, whereas the remaining 35% (9/26) provided implementation guidelines. Of the final 26 papers, the quality of 21 (81%) was assessed as poor. A total of 28 enablers was identified; 8 (29%) were new in this study. A total of 18 barriers was identified; 5 (28%) were newly found. Most of these newly identified factors were related to information and technology. Actionable recommendations for the implementation of AI toward achieving an LHS were provided by mapping the findings to a 3-horizon framework.

CONCLUSIONS

Significant issues exist in implementing AI in health care. Shifting from validating data sets to working with live data is challenging. This review incorporated the identified enablers and barriers into a 3-horizon framework, offering actionable recommendations for implementing AI analytics to achieve an LHS. The findings of this study can assist hospitals in steering their strategic planning toward successful adoption of AI.

Engaging Multidisciplinary Clinical Users in the Design of an Artificial Intelligence-Powered Graphical User Interface for Intensive Care Unit Instability Decision Support

BACKGROUND

Critical instability forecast and treatment can be optimized by artificial intelligence (AI)-enabled clinical decision support. It is important that the user-facing display of AI output facilitates clinical thinking and workflow for all disciplines involved in bedside care.

OBJECTIVES

Our objective is to engage multidisciplinary users (physicians, nurse practitioners, physician assistants) in the development of a graphical user interface (GUI) to present an AI-derived risk score.

METHODS

Intensive care unit (ICU) clinicians participated in focus groups seeking input on instability risk forecast presented in a prototype GUI. Two stratified rounds (three focus groups [only nurses, only providers, then combined]) were moderated by a focus group methodologist. After round 1, GUI design changes were made and presented in round 2. Focus groups were recorded, transcribed, and deidentified transcripts independently coded by three researchers. Codes were coalesced into emerging themes.

RESULTS

Twenty-three ICU clinicians participated (11 nurses, 12 medical providers [3 mid-level and 9 physicians]). Six themes emerged: (1) analytics transparency, (2) graphical interpretability, (3) impact on practice, (4) value of trend synthesis of dynamic patient data, (5) decisional weight (weighing AI output during decision-making), and (6) display location (usability, concerns for patient/family GUI view). Nurses emphasized having GUI objective information to support communication and optimal GUI location. While providers emphasized need for recommendation interpretability and concern for impairing trainee critical thinking. All disciplines valued synthesized views of vital signs, interventions, and risk trends but were skeptical of placing decisional weight on AI output until proven trustworthy.

CONCLUSION

Gaining input from all clinical users is important to consider when designing AI-derived GUIs. Results highlight that health care intelligent decisional support systems technologies need to be transparent on how they work, easy to read and interpret, cause little disruption to current workflow, as well as decisional support components need to be used as an adjunct to human decision-making.

AIDH Summit 2022 - The effect of digitisation on the safe management of anticoagulants

BACKGROUND

Anticoagulants are high-risk medications and are a common cause of adverse events of hospitalised inpatients. The incidence of adverse events involving anticoagulants has remained relatively unchanged over the past two decades, suggesting novel approaches are required to address this persistent issue. Electronic medication management systems (eMMS) offer strategies to help reduce medication incidents and adverse drug events, yet poor system design can introduce new error types.

OBJECTIVE

To evaluate the effect of the introduction of an electronic medical record (EMR) on the quality and safety of therapeutic anticoagulation management.

METHODS

A retrospective, observational pre/post study was conducted, analysing real-world data across five hospital sites in a single health service. Four metrics were compared one year pre- and one year post-EMR implementation. They included clinician-reported medication incidents, toxic pathology results, hospital-acquired bleeding complications (HACs) and rate of heparin-induced thrombocytopenia. Further sub-analyses of patients experiencing HACs in the post-EMR period, identified key opportunities for intervention to maximise safety and quality of anticoagulation within an eMMS.

RESULTS

A significant reduction in HACs was observed in the post-EMR implementation period (mean (SD) =12.1 (4.4)/month, vs. mean (SD) =7.8 (3.5)/month; p=0.01). The categorisation of potential EMR design enhancements found that new automated clinical decision support or improved pathology result integration would be suitable to mitigate future HACs in an eMMS. There was no significant difference in the mean monthly clinician-reported incident rates for anticoagulants or the rate of toxic pathology results in the pre- versus post-EMR implementation period. A 62.5% reduction in the cases of heparin-induced thrombocytopenia were observed in the post-EMR implementation period.

CONCLUSION

The implementation of an EMR improves clinical care outcomes for patients receiving anticoagulation. System design plays a significant role in mitigating the risks associated with anticoagulants and consideration must be given to optimising eMMS.

Toward a Learning Health Care System: A Systematic Review and Evidence-Based Conceptual Framework for Implementation of Clinical Analytics in a Digital Hospital

Objective  A learning health care system (LHS) uses routinely collected data to continuously monitor and improve health care outcomes. Little is reported on the challenges and methods used to implement the analytics underpinning an LHS. Our aim was to systematically review the literature for reports of real-time clinical analytics implementation in digital hospitals and to use these findings to synthesize a conceptual framework for LHS implementation.

Methods  Embase, PubMed, and Web of Science databases were searched for clinical analytics derived from electronic health records in adult inpatient and emergency department settings between 2015 and 2021. Evidence was coded from the final study selection that related to (1) dashboard implementation challenges, (2) methods to overcome implementation challenges, and (3) dashboard assessment and impact. The evidences obtained, together with evidence extracted from relevant prior reviews, were mapped to an existing digital health transformation model to derive a conceptual framework for LHS analytics implementation.

Results  A total of 238 candidate articles were reviewed and 14 met inclusion criteria. From the selected studies, we extracted 37 implementation challenges and 64 methods employed to overcome such challenges. We identified common approaches for evaluating the implementation of clinical dashboards. Six studies assessed clinical process outcomes and only four studies evaluated patient health outcomes. A conceptual framework for implementing the analytics of an LHS was developed.

Conclusion  Health care organizations face diverse challenges when trying to implement real-time data analytics. These challenges have shifted over the past decade. While prior reviews identified fundamental information problems, such as data size and complexity, our review uncovered more postpilot challenges, such as supporting diverse users, workflows, and user-interface screens. Our review identified practical methods to overcome these challenges which have been incorporated into a conceptual framework. It is hoped this framework will support health care organizations deploying near-real-time clinical dashboards and progress toward an LHS.

Machine learning models for diabetes management in acute care using electronic medical records: A systematic review

BACKGROUND

Machine learning (ML) is a subset of Artificial Intelligence (AI) that is used to predict and potentially prevent adverse patient outcomes. There is increasing interest in the application of these models in digital hospitals to improve clinical decision-making and chronic disease management, particularly for patients with diabetes. The potential of ML models using electronic medical records (EMR) to improve the clinical care of hospitalised patients with diabetes is currently unknown.

OBJECTIVE

The aim was to systematically identify and critically review the published literature examining the development and validation of ML models using EMR data for improving the care of hospitalised adult patients with diabetes.

METHODS

The Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA) guidelines were followed. Four databases were searched (Embase, PubMed, IEEE and Web of Science) for studies published between January 2010 to January 2022. The reference lists of the eligible articles were manually searched. Articles that examined adults and both developed and validated ML models using EMR data were included. Studies conducted in primary care and community care settings were excluded. Studies were independently screened and data was extracted using Covidence® systematic review software. For data extraction and critical appraisal, the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) was followed. Risk of bias was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). Quality of reporting was assessed by adherence to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guideline. The IJMEDI checklist was followed to assess quality of ML models and the reproducibility of their outcomes. The external validation methodology of the studies was appraised.

RESULTS

Of the 1317 studies screened, twelve met inclusion criteria. Eight studies developed ML models to predict disglycaemic episodes for hospitalized patients with diabetes, one study developed a ML model to predict total insulin dosage, two studies predicted risk of readmission, and one study improved the prediction of hospital readmission for inpatients with diabetes. All included studies were heterogeneous with regard to ML types, cohort, input predictors, sample size, performance and validation metrics and clinical outcomes. Two studies adhered to the TRIPOD guideline. The methodological reporting of all the studies was evaluated to be at high risk of bias. The quality of ML models in all studies was assessed as poor. Robust external validation was not performed on any of the studies. No models were implemented or evaluated in routine clinical care.

CONCLUSIONS

This review identified a limited number of ML models which were developed to improve inpatient management of diabetes. No ML models were implemented in real hospital settings. Future research needs to enhance the development, reporting and validation steps to enable ML models for integration into routine clinical care.

Digital health and precision prevention: shifting from disease-centred care to consumer-centred health

Digital disruption and transformation of health care is occurring rapidly. Concurrently, a global syndemic of preventable chronic disease is crippling healthcare systems and accelerating the effect of the COVID-19 pandemic. Healthcare investment is paradoxical; it prioritises disease treatment over prevention. This is an inefficient break-fix model versus a person-centred predict-prevent model. It is easy to reward and invest in acute health systems because activity is easily measured and therefore funded. Social, environmental and behavioural health determinants explain ~70% of health variance; yet, we cannot measure these community data contemporaneously or at population scale. The dawn of digital health and the digital citizen can initiate a precision prevention era, where consumer-centred, real-time data enables a new ability to count and fund population health, making disease prevention 'matter'. Then, precision decision making, intervention and policy to target preventable chronic disease (e.g. obesity) can be realised. We argue for, identify barriers to, and propose three horizons for digital health transformation of population health towards precision prevention of chronic disease, demonstrating childhood obesity as a use case. Clinicians, researchers and policymakers can commence strategic planning and investment for precision prevention of chronic disease to advance a mature, value-based model that will ensure healthcare sustainability in Australia and globally.

Managing the Digital Disruption Associated with COVID-19-Driven Rapid Digital Transformation in Brisbane, Australia

BACKGROUND

The COVID-19 pandemic has forced rapid digital transformation of many health systems. These innovations are now entering the literature, but there is little focus on the resulting disruption.

OBJECTIVE

We describe the implementation of digital innovations during the COVID-19 response of Australia's largest health service, Metro North (in Brisbane, Queensland), the challenges of the subsequent digital disruption, how these were managed, and lessons learned.

METHODS

Prior to the COVID-19 pandemic, the Australian state of Queensland created the Queensland Digital Clinical Charter, which provides guidance for the development of digital health programs. The guidelines utilize three horizons: digitizing workflows, leveraging digital data to transform clinical care, and reimagining new and innovative models of care. The technical response to COVID-19 in Metro North is described across these horizons. The rapid digital response caused significant disruption to health care delivery; management of the disruption and the outcomes are detailed. This is a participatory action research project, with members of the research team assisting with leading the implementation project informing the case report content.

RESULTS

Several digital innovations were introduced across Metro North during the COVID-19 response. This resulted in significant disruption creating digital hypervigilance, digital deceleration, data discordance, and postdigital "depression." Successful management of the digital disruption minimized the negative effects of rapid digital transformation, and contributed to the effective management of the pandemic in Queensland.

CONCLUSION

The rapid digital transformation in Metro North during COVID-19 was successful in several aspects; however, ongoing challenges remain. These include the need to improve data sharing and increase interoperability. Importantly, the innovations need to be evaluated to ensure that Metro North can capitalize on these changes and incorporate them into long-term routine practice. Moving forward, it will be essential to manage not only the pandemic, but increasingly, the resultant digital disruption.

Moving Faster than the COVID-19 Pandemic: The Rapid, Digital Transformation of a Public Health System

Background  Queensland, Australia has been successful in containing the COVID-19 pandemic. Underpinning that response has been a highly effective virus containment strategy which relies on identification, isolation, and contact tracing of cases. The dramatic emergence of the COVID-19 pandemic rendered traditional paper-based systems for managing contact tracing no longer fit for purpose. A rapid digital transformation of the public health contact tracing system occurred to support this effort.

Objectives  The objectives of the digital transformation were to shift legacy systems (paper or standalone electronic systems) to a digitally enabled public health system, where data are centered around the consumer rather than isolated databases. The objective of this paper is to outline this case study and detail the lessons learnt to inform and give confidence to others contemplating digitization of public health systems in response to the COVID-19 pandemic.

Methods  This case study is set in Queensland, Australia. Universal health care is available. A multidisciplinary team was established consisting of clinical informaticians, developers, data strategists, and health information managers. An agile “pair-programming” approach was undertaken to application development and extensive change efforts were made to maximize adoption of the new digital workflows. Data governance and flows were changed to support rapid management of the pandemic.

Results  The digital coronavirus application (DCOVA) is a web-based application that securely captures information about people required to quarantine and creates a multiagency secure database to support a successful containment strategy.

Conclusion  Most of the literature surrounding digital transformation allows time for significant consultation, which was simply not possible under crisis conditions. Our observation is that staff was willing to adopt new digital systems because the reason for change (the COVID-19 pandemic) was clearly pressing. This case study highlights just how critical a unified purpose, is to successful, rapid digital transformation.