A framework for analysing learning health systems: Are we removing the most impactful barriers?

Optimizing the Clinical Direction of Artificial Intelligence With Health Policy: A Narrative Review of the Literature

Artificial intelligence (AI) has the ability to completely transform the healthcare industry by enhancing diagnosis, treatment, and resource allocation. To ensure patient safety and equitable access to healthcare, it also presents ethical and practical issues that need to be carefully addressed. Its integration into healthcare is a crucial topic. To realize its full potential, however, the ethical issues around data privacy, prejudice, and transparency, as well as the practical difficulties posed by workforce adaptability and statutory frameworks, must be addressed. While there is growing knowledge about the advantages of AI in healthcare, there is a significant lack of knowledge about the moral and practical issues that come with its application, particularly in the setting of emergency and critical care. The majority of current research tends to concentrate on the benefits of AI, but thorough studies that investigate the potential disadvantages and ethical issues are scarce. The purpose of our article is to identify and examine the ethical and practical difficulties that arise when implementing AI in emergency medicine and critical care, to provide solutions to these issues, and to give suggestions to healthcare professionals and policymakers. In order to responsibly and successfully integrate AI in these important healthcare domains, policymakers and healthcare professionals must collaborate to create strong regulatory frameworks, safeguard data privacy, remove prejudice, and give healthcare workers the necessary training.

Advancement, barriers and collaboration: the ABC's of addressing challenges and designing solutions between front-line physicians and business-oriented leaders

BACKGROUND

The complexity of US healthcare has been increasing for many years, requiring clinicians and learners to understand care delivery systems in addition to clinical sciences. Thus, there has been a major push to educate faculty and trainees on healthcare functionality. This comes as hospitals expand into health systems requiring the help of more sophisticated expertise of departments such as operations excellence when problem-solving. As a medical student with a background in operations excellence, medical education leader and clinical administration leader all currently facilitating this transition, we wanted to reflect on the barriers we have experienced in clinical implementation of quality improvement projects and educating learners on the impact of operations excellence principles in their clinical education.

METHODS

The ideas presented in this article were the result of a several collaborative discussion between the authors, on the key challenges to adopting operations excellence principles into health system science education. In an effort to add context to this reflection through the current body of research present, they supplemented a literature review on the topic which included 86 studies published between 2013 and 2021 regarding health systems science and healthcare leadership engagement in the USA. The themes that intersected between the literature review and the discussions were then expanded on in this paper.

RESULTS

Through this process, we identified four challenges: (1) the difference in thinking styles, which we term, 'mental model differences'; (2) the strategic nature of process improvement projects and how that collides with physician priorities, or 'the chess game of stakeholder engagement'; (3) the language and precise methodology, or 'consistency of language and need for administrative resilience' and (4) the issue of teaching these concepts or bridging the learning gap.'

CONCLUSION

In an increasingly complex healthcare landscape, physicians and trainee's need to bridge gaps between the mental models of administrative and clinical workflow.

Barriers to Adoption of Tailored Drug-Drug Interaction Clinical Decision Support

OBJECTIVE

Despite the benefits of the tailored drug-drug interaction (DDI) alerts and the broad dissemination strategy, the uptake of our tailored DDI alert algorithms that are enhanced with patient-specific and context-specific factors has been limited. The goal of the study was to examine barriers and health care system dynamics related to implementing tailored DDI alerts and identify the factors that would drive optimization and improvement of DDI alerts.

METHODS

We employed a qualitative research approach, conducting interviews with a participant interview guide framed based on Proctor's taxonomy of implementation outcomes and informed by the Theoretical Domains Framework. Participants included pharmacists with informatics roles within hospitals, chief medical informatics officers, and associate medical informatics directors/officers. Our data analysis was informed by the technique used in grounded theory analysis, and the reporting of open coding results was based on a modified version of the Safety-Related Electronic Health Record Research Reporting Framework.

RESULTS

Our analysis generated 15 barriers, and we mapped the interconnections of these barriers, which clustered around three entities (i.e., users, organizations, and technical stakeholders). Our findings revealed that misaligned interests regarding DDI alert performance and misaligned expectations regarding DDI alert optimizations among these entities within health care organizations could result in system inertia in implementing tailored DDI alerts.

CONCLUSION

Health care organizations primarily determine the implementation and optimization of DDI alerts, and it is essential to identify and demonstrate value metrics that health care organizations prioritize to enable tailored DDI alert implementation. This could be achieved via a multifaceted approach, such as partnering with health care organizations that have the capacity to adopt tailored DDI alerts and identifying specialists who know users' needs, liaise with organizations and vendors, and facilitate technical stakeholders' work. In the future, researchers can adopt the systematic approach to study tailored DDI implementation problems from other system perspectives (e.g., the vendors' system).

Learning health systems in low-income and middle-income countries: exploring evidence and expert insights

Introduction

Learning health systems (LHS) is a multifaceted subject. This paper reviewed current concepts as well as real-world experiences of LHS, drawing on published and unpublished knowledge in order to identify and describe important principles and practices that characterise LHS in low/middle-income country (LMIC) settings.

Methods

We adopted an exploratory approach to the literature review, recognising there are limited studies that focus specifically on system-wide learning in LMICs, but a vast set of connected bodies of literature. 116 studies were included, drawn from an electronic literature search of published and grey literature. In addition, 17 interviews were conducted with health policy and research experts to gain experiential knowledge.

Results

The findings were structured by eight domains on learning enablers. All of these interact with one another and influence actors from community to international levels.

We found that learning comes from the connection between information, deliberation, and action. Moreover, these processes occur at different levels. It is therefore important to consider experiential knowledge from multiple levels and experiences. Creating spaces and providing resources for communities, staff and managers to deliberate on their challenges and find solutions has political implications, however, and is challenging, particularly when resources are constrained, funding and accountability are fragmented and the focus is short-term and narrow. Nevertheless, we can learn from countries that have managed to develop institutional mechanisms and human capacities which help health systems respond to changing environments with ‘best fit’ solutions.

Conclusion

Health systems are knowledge producers, but learning is not automatic. It needs to be valued and facilitated. Everyday governance of health systems can create spaces for reflective practice and learning within routine processes at different levels. This article highlights important enablers, but there remains much work to be done on developing this field of knowledge.

Clarifying the concept of a learning health system for healthcare delivery organizations: Implications from a qualitative analysis of the scientific literature

The "learning health system" (LHS) concept has been defined in broad terms, which makes it challenging for health system leaders to determine exactly what is required to transform their organization into an LHS. This study provides a conceptual map of the LHS landscape by identifying the activities, principles, tools, and conditions that LHS researchers have associated with the concept. Through a multi-step screening process, two researchers identified 79 publications from PubMed (published before January 2020) that contained information relevant to the question, "What work is required of a healthcare organization that is operating as an LHS?" Those publications were coded as to whether or not they referenced each of 94 LHS elements in the taxonomy developed by the study team. This taxonomy, named the Learning Health Systems Consolidated Framework (LHS-CF), organizes the elements into five "bodies of work" (organizational learning, translation of evidence into practice, building knowledge, analyzing clinical data, and engaging stakeholders) and four "enabling conditions" (workforce skilled for LHS work, data systems and informatics technology in place, organization invests resources in LHS work, and supportive organizational culture). We report the frequency that each of the 94 elements was referenced across the 79 publications. The four most referenced elements were: "organization builds knowledge or evidence," "quality improvement practices are standard practice," "patients and family members are actively engaged," and "organizational culture emphasizes and supports learning." By dissecting the LHS construct into its component elements, the LHS-CF taxonomy can serve as a useful tool for LHS researchers and practitioners in defining the aspects of LHS they are addressing. By assessing how often each element is referenced in the literature, the study provides guidance to health system leaders as to how their organization needs to evolve in order to become an LHS - while also recognizing that each organization should emphasize elements that are most aligned with their mission and goals.

How can we discover the most valuable types of big data and artificial intelligence-based solutions? A methodology for the efficient development of the underlying analytics that improve care

BACKGROUND

Much has been invested in big data and artificial intelligence-based solutions for healthcare. However, few applications have been implemented in clinical practice. Early economic evaluations can help to improve decision-making by developers of analytics underlying these solutions aiming to increase the likelihood of successful implementation, but recommendations about their use are lacking. The aim of this study was to develop and apply a framework that positions best practice methods for economic evaluations alongside development of analytics, thereby enabling developers to identify barriers to success and to select analytics worth further investments.

METHODS

The framework was developed using literature, recommendations for economic evaluations and by applying the framework to use cases (chronic lymphocytic leukaemia (CLL), intensive care, diabetes). First, the feasibility of developing clinically relevant analytics was assessed and critical barriers to successful development and implementation identified. Economic evaluations were then used to determine critical thresholds and guide investment decisions.

RESULTS

When using the framework to assist decision-making of developers of analytics, continuing development was not always feasible or worthwhile. Developing analytics for progressive CLL and diabetes was clinically relevant but not feasible with the data available. Alternatively, developing analytics for newly diagnosed CLL patients was feasible but continuing development was not considered worthwhile because the high drug costs made it economically unattractive for potential users. Alternatively, in the intensive care unit, analytics reduced mortality and per-patient costs when used to identify infections (- 0.5%, - €886) and to improve patient-ventilator interaction (- 3%, - €264). Both analytics have the potential to save money but the potential benefits of analytics that identify infections strongly depend on infection rate; a higher rate implies greater cost-savings.

CONCLUSIONS

We present a framework that stimulates efficiency of development of analytics for big data and artificial intelligence-based solutions by selecting those applications of analytics for which development is feasible and worthwhile. For these applications, results from early economic evaluations can be used to guide investment decisions and identify critical requirements.

Mobilizing health district management teams through digital tools: Lessons from the District.Team initiative in Benin and Guinea using an action research methodology

BACKGROUND

Improving capacities of health systems to quickly respond to emerging health issues, requires a health information system (HIS) that facilitates evidence-informed decision-making at the operational level. In many sub-Saharan African countries, HIS are mostly designed to feed decision-making purposes at the central level with limited feedback and capabilities to take action from data at the operational level. This article presents the case of an eHealth innovation designed to capacitate health district management teams (HDMTs) through participatory evidence production and peer-to-peer exchange.

METHODS

We used an action research design to develop the eHealth initiative called "District.Team," a web-based and facilitated platform targeting HDMTs that was tested in Benin and Guinea from January 2016 to September 2017. On District.Team, rounds of knowledge sharing processes were organized into cycles of five steps. Quantitative and qualitative data were collected to assess the participation of HDMTs and identify enablers and barriers of using District.Team.

RESULTS

Participation of HDMTs in District.Team varied between cycles and steps. In Benin, 79% to 94% of HDMTs filled in the online questionnaire per cycle compared to 61% to 100% in Guinea per cycle. In Benin, 26% to 41% of HDMTs shared a commentary on the results published on the platform while 21% to 47% participated in the online discussion forum. In Guinea, only 3% to 8% of HDMTs shared a commentary on the results published on the platform while 8% to 74% participated in the online discussion forum. Five groups of factors affected the participation: characteristics of the digital tools, the quality of the facilitation, profile of participants, shared content and data, and finally support from health authorities.

CONCLUSION

District.Team has shown that knowledge management platforms and processes valuing horizontal knowledge sharing among peers at the decentralized level of health systems are feasible in limited resource settings.

Enabling a learning healthcare system with automated computer protocols that produce replicable and personalized clinician actions

Clinical decision-making is based on knowledge, expertise, and authority, with clinicians approving almost every intervention-the starting point for delivery of "All the right care, but only the right care," an unachieved healthcare quality improvement goal. Unaided clinicians suffer from human cognitive limitations and biases when decisions are based only on their training, expertise, and experience. Electronic health records (EHRs) could improve healthcare with robust decision-support tools that reduce unwarranted variation of clinician decisions and actions. Current EHRs, focused on results review, documentation, and accounting, are awkward, time-consuming, and contribute to clinician stress and burnout. Decision-support tools could reduce clinician burden and enable replicable clinician decisions and actions that personalize patient care. Most current clinical decision-support tools or aids lack detail and neither reduce burden nor enable replicable actions. Clinicians must provide subjective interpretation and missing logic, thus introducing personal biases and mindless, unwarranted, variation from evidence-based practice. Replicability occurs when different clinicians, with the same patient information and context, come to the same decision and action. We propose a feasible subset of therapeutic decision-support tools based on credible clinical outcome evidence: computer protocols leading to replicable clinician actions (eActions). eActions enable different clinicians to make consistent decisions and actions when faced with the same patient input data. eActions embrace good everyday decision-making informed by evidence, experience, EHR data, and individual patient status. eActions can reduce unwarranted variation, increase quality of clinical care and research, reduce EHR noise, and could enable a learning healthcare system.

Why We Are Losing the War Against COVID-19 on the Data Front and How to Reverse the Situation

With over 117 million COVID-19–positive cases declared and the death count approaching 3 million, we would expect that the highly digitalized health systems of high-income countries would have collected, processed, and analyzed large quantities of clinical data from patients with COVID-19. Those data should have served to answer important clinical questions such as: what are the risk factors for becoming infected? What are good clinical variables to predict prognosis? What kinds of patients are more likely to survive mechanical ventilation? Are there clinical subphenotypes of the disease? All these, and many more, are crucial questions to improve our clinical strategies against the epidemic and save as many lives as possible. One might assume that in the era of big data and machine learning, there would be an army of scientists crunching petabytes of clinical data to answer these questions. However, nothing could be further from the truth. Our health systems have proven to be completely unprepared to generate, in a timely manner, a flow of clinical data that could feed these analyses. Despite gigabytes of data being generated every day, the vast quantity is locked in secure hospital data servers and is not being made available for analysis. Routinely collected clinical data are, by and large, regarded as a tool to inform decisions about individual patients, and not as a key resource to answer clinical questions through statistical analysis. The initiatives to extract COVID-19 clinical data are often promoted by private groups of individuals and not by health systems, and are uncoordinated and inefficient. The consequence is that we have more clinical data on COVID-19 than on any other epidemic in history, but we have failed to analyze this information quickly enough to make a difference. In this viewpoint, we expose this situation and suggest concrete ideas that health systems could implement to dynamically analyze their routine clinical data, becoming learning health systems and reversing the current situation.

Removing barriers for digital health through organizing ambidexterity in hospitals

Aim

Hospitals noticeably struggle with maintaining hundreds of IT systems and applications in compliance with the latest IT standards and regulations. Thus, hospitals search for efficient opportunities to discover and integrate useful digital health innovations into their existing IT landscapes. In addition, although a multitude of digital innovations from digital health startups enter the market, numerous barriers impede their successful implementation and adoption. Against this background, the aim of this study was to explore typical digital innovation barriers in hospitals, and to assess how a hospital data management platform (HDMP) architecture might help hospitals to extract such innovative capabilities.

Subject and methods

Based on the concept of organizational ambidexterity (OA), we pursued a qualitative mixed-methods approach. First, we explored and consolidated innovation barriers through a systematic literature review, interviews with 20 startup representatives, and a focus group interview with a hospital IT team and the CEO of an HDMP provider. Finally, we conducted a case-study analysis of 36 digital health startups to explore and conceptualize the potential impact of DI and apply the morphological method to synthesize our findings from a multi-level perspective.

Results

We first provide a systematic and conceptual overview of typical barriers for digital innovation in hospitals. Hereupon, we explain how an HDMP might enable hospitals to mitigate such barriers and extract value from digital innovations at both individual and organizational level.

Conclusion

Our results imply that an HDMP can help hospitals to approach organizational ambidexterity through integrating and maintaining hundreds of systems and applications, which allows for a structured and controlled integration of external digital innovations.

LAGOS: learning health systems and how they can integrate with patient care

PROBLEM

Learning health systems (LHS) are an underexplored concept. How LHS will operate in clinical practice is not well understood. This paper investigates the relationships between LHS, clinical care process specifications (CCPS) and the established levels of medical practice to enable LHS integration into daily healthcare practice.

METHODS

Concept analysis and thematic analysis were used to develop an LHS characterisation. Pathway theory was used to create a framework by relating LHS, CCPS, health information systems and the levels of medical practice. A case study approach evaluates the framework in an established health informatics project.

RESULTS

Five concepts were identified and used to define the LHS learning cycle. A framework was developed with five pathways, each having three levels of practice specificity spanning population to precision medicine. The framework was evaluated through application to case studies not previously understood to be LHS.

DISCUSSION

Clinicians show limited understanding of LHS, increasing resistance and limiting adoption and integration into care routine. Evaluation of the presented framework demonstrates that its use enables: (1) correct analysis and characterisation of LHS; (2) alignment and integration into the healthcare conceptual setting; (3) identification of the degree and level of patient application; and (4) impact on the overall healthcare system.

CONCLUSION

This paper contributes a theoretical framework for analysis, characterisation and use of LHS. The framework allows clinicians and informaticians to correctly identify, characterise and integrate LHS within their daily routine. The overall contribution improves understanding, practice and evaluation of the LHS application in healthcare.