How has Guinea learnt from the response to outbreaks? A learning health system analysis.

INTRODUCTION: Learning is a key attribute of a resilient health system and, therefore, is central to health system strengthening. The main objective of this study was to analyse how Guinea's health system has learnt from the response to outbreaks between 2014 and 2021. METHODS: We used a retrospective longitudinal single embedded case study design, applying the framework conceptualised by Sheikh and Abimbola for analysing learning health systems. Data were collected employing a mixed methods systematic review carried out in March 2022 and an online survey conducted in April 2022. RESULTS: The 70 reports included in the evidence synthesis were about the 2014-2016 Ebola virus disease (EVD), Measles, Lassa Fever, COVID-19, 2021 EVD and Marburg virus disease. The main lessons were from 2014 to 2016 EVD and included: early community engagement in the response, social mobilisation, prioritising investment in health personnel, early involvement of anthropologists, developing health infrastructure and equipment and ensuring crisis communication. They were learnt through information (research and experts' opinions), action/practice and double-loop and were progressively incorporated in the response to future outbreaks through deliberation, single-loop, double-loop and triple-loop learning. However, advanced learning aspects (learning through action, double-loop and triple-loop) were limited within the health system. Nevertheless, the health system successfully controlled COVID-19, the 2021 EVD and Marburg virus disease. Survey respondents' commonly reported that enablers were the creation of the national agency for health security and support from development partners. Barriers included cultural and political issues and lack of funding. Common recommendations included establishing a knowledge management unit within the Ministry of Health with representatives at regional and district levels, investing in human capacities and improving the governance and management system. CONCLUSION: Our study highlights the importance of learning. The health system performed well and achieved encouraging and better outbreak response outcomes over time with learning that occurred.

Developing and Implementing Predictive Models in a Learning Healthcare System: Traditional and Artificial Intelligence Approaches in the Veterans Health Administration.

Predicting clinical risk is an important part of healthcare and can inform decisions about treatments, preventive interventions, and provision of extra services. The field of predictive models has been revolutionized over the past two decades by electronic health record data; the ability to link such data with other demographic, socioeconomic, and geographic information; the availability of high-capacity computing; and new machine learning and artificial intelligence methods for extracting insights from complex datasets. These advances have produced a new generation of computerized predictive models, but debate continues about their development, reporting, validation, evaluation, and implementation. In this review we reflect on more than 10 years of experience at the Veterans Health Administration, the largest integrated healthcare system in the United States, in developing, testing, and implementing such models at scale. We report lessons from the implementation of national risk prediction models and suggest an agenda for research.

Applying learning health systems thinking in codeveloping integrated tuberculosis interventions in the contexts of COVID-19.

The COVID-19 pandemic reversed much of global progress made in combatting tuberculosis, with South Africa experiencing one of the largest impacts on tuberculosis detection. The aim of this paper is to share our experiences in applying learning health systems (LHS) thinking to the codevelopment of an intervention improving an integrated response to COVID-19 and tuberculosis in a South African district. A sequential partially mixed-methods study was undertaken between 2018 and 2021 in the district of Amajuba in KwaZulu-Natal. Here, we report on the formulation of a Theory of Change, codesigning and refining proposed interventions, and piloting and evaluating codesigned interventions in primary healthcare facilities, through an LHS lens. Following the establishment and formalisation of a district Learning Community, diagnostic work and a codevelopment of a theory of change, intervention packages tailored according to pandemic lockdowns were developed, piloted and scaled up. This process illustrates how a community of learning can generate more responsive, localised interventions, and suggests that the establishment of a shared space of research governance can provide a degree of resilience to facilitate adaption to external shocks. Four main lessons have been gleaned from our experience in adopting an LHS approach in a South African district, which are (1) the importance of building and sustaining relationships, (2) the utility of colearning, coproduction and adaptive capacity, (3) the centrality of theory-driven systems strengthening and (4) reflections on LHS as a framework.

Using a learning health system framework to examine COVID-19 pandemic planning and response at a Canadian Health Centre.

BACKGROUND: The COVID-19 pandemic has presented a unique opportunity to explore how health systems adapt under rapid and constant change and develop a better understanding of health system transformation. Learning health systems (LHS) have been proposed as an ideal structure to inform a data-driven response to a public health emergency like COVID-19. The aim of this study was to use a LHS framework to identify assets and gaps in health system pandemic planning and response during the initial stages of the COVID-19 pandemic at a single Canadian Health Centre. METHODS: This paper reports the data triangulation stage of a concurrent triangulation mixed methods study which aims to map study findings onto the LHS framework. We used a triangulation matrix to map quantitative (textual and administrative sources) and qualitative (semi-structured interviews) data onto the seven characteristics of a LHS and identify assets and gaps related to health-system receptors and research-system supports. RESULTS: We identified several health system assets within the LHS characteristics, including appropriate decision supports and aligned governance. Gaps were identified in the LHS characteristics of engaged patients and timely production and use of research evidence. CONCLUSION: The LHS provided a useful framework to examine COVID-19 pandemic response measures. We highlighted opportunities to strengthen the LHS infrastructure for rapid integration of evidence and patient experience data into future practice and policy changes.

The comparative effectiveness of COVID-19 monoclonal antibodies: A learning health system randomized clinical trial.

BACKGROUND: Monoclonal antibodies (mAb) that neutralize SARS-CoV-2 decrease hospitalization and death compared to placebo in patients with mild to moderate COVID-19; however, comparative effectiveness is unknown. We report the comparative effectiveness of bamlanivimab, bamlanivimab-etesevimab, and casirivimab-imdevimab. METHODS: A learning health system platform trial in a U.S. health system enrolled patients meeting mAb Emergency Use Authorization criteria. An electronic health record-embedded application linked local mAb inventory to patient encounters and provided random mAb allocation. Primary outcome was hospital-free days to day 28. Primary analysis was a Bayesian model adjusting for treatment location, age, sex, and time. Inferiority was defined as 99% posterior probability of an odds ratio < 1. Equivalence was defined as 95% posterior probability the odds ratio is within a given bound. FINDINGS: Between March 10 and June 25, 2021, 1935 patients received treatment. Median hospital-free days were 28 (IQR 28, 28) for each mAb. Mortality was 0.8% (1/128), 0.8% (7/885), and 0.7% (6/922) for bamlanivimab, bamlanivimab-etesevimab, and casirivimab-imdevimab, respectively. Relative to casirivimab-imdevimab (n = 922), median adjusted odds ratios were 0.58 (95% credible interval [CI] 0.30-1.16) and 0.94 (95% CI 0.72-1.24) for bamlanivimab (n = 128) and bamlanivimab-etesevimab (n = 885), respectively. These odds ratios yielded 91% and 94% probabilities of inferiority of bamlanivimab versus bamlanivimab-etesevimab and casirivimab-imdevimab, and an 86% probability of equivalence between bamlanivimab-etesevimab and casirivimab-imdevimab. INTERPRETATION: Among patients with mild to moderate COVID-19, bamlanivimab-etesevimab or casirivimab-imdevimab treatment resulted in 86% probability of equivalence. No treatment met prespecified criteria for statistical equivalence. Median hospital-free days to day 28 were 28 (IQR 28, 28) for each mAb. FUNDING AND REGISTRATION: This work received no external funding. The U.S. government provided the reported mAb. This trial is registered at ClinicalTrials.gov, NCT04790786.

Building a Learning Health System: Creating an Analytical Workflow for Evidence Generation to Inform Institutional Clinical Care Guidelines.

BACKGROUND: One key aspect of a learning health system (LHS) is utilizing data generated during care delivery to inform clinical care. However, institutional guidelines that utilize observational data are rare and require months to create, making current processes impractical for more urgent scenarios such as those posed by the COVID-19 pandemic. There exists a need to rapidly analyze institutional data to drive guideline creation where evidence from randomized control trials are unavailable. OBJECTIVES: This article provides a background on the current state of observational data generation in institutional guideline creation and details our institution's experience in creating a novel workflow to (1) demonstrate the value of such a workflow, (2) demonstrate a real-world example, and (3) discuss difficulties encountered and future directions. METHODS: Utilizing a multidisciplinary team of database specialists, clinicians, and informaticists, we created a workflow for identifying and translating a clinical need into a queryable format in our clinical data warehouse, creating data summaries and feeding this information back into clinical guideline creation. RESULTS: Clinical questions posed by the hospital medicine division were answered in a rapid time frame and informed creation of institutional guidelines for the care of patients with COVID-19. The cost of setting up a workflow, answering the questions, and producing data summaries required around 300 hours of effort and $300,000 USD. CONCLUSION: A key component of an LHS is the ability to learn from data generated during care delivery. There are rare examples in the literature and we demonstrate one such example along with proposed thoughts of ideal multidisciplinary team formation and deployment.

Healthcare personnel early return-to-work program after higher-risk SARS-CoV-2 exposure: A learning health system quality improvement project.

BACKGROUND: Incidence of health care personnel (HCP) with a higher-risk SARS-CoV-2 exposure and subsequent 14-day quarantine period adds substantial burden on the workforce. Implementation of an early return-to-work (RTW) program may reduce quarantine periods for asymptomatic HCP and reduce workforce shortages during the COVID-19 pandemic. METHODS: This observational quality improvement study included asymptomatic HCP of a multi-facility health care system with higher-risk workplace or non-household community SARS-CoV-2 exposure ≤4 days. The program allowed HCP to return to work 8 days after exposure if they remained asymptomatic through day 7 with day 5-7 SARS-CoV-2 nucleic acid amplification test result negative. RESULTS: Between January 4 and June 25, 2021, 384 HCP were enrolled, 333 (86.7%) remained asymptomatic and of these, 323 (97%) tested negative and were early RTW eligible. Mean days in quarantine was 8.16 (SD 2.40). Median day of early RTW was 8 (range 6-9, IQR 8-8). Mean days saved from missed work was 1.84 (SD 0.52). A total of 297 (92%) HCP did RTW ≤10 days from exposure and days saved from missed work was 546.48. CONCLUSIONS: Implementing an HCP early RTW program is a clinical approach for COVID-19 workplace safety that can increase staffing availability, while maintaining a low risk of SARS-CoV-2 transmission.

Telemedicine Use and Health-Related Concerns of Patients With Chronic Conditions During COVID-19: Survey of Members of Online Health Communities.

BACKGROUND: It has been widely communicated that individuals with underlying health conditions are at higher risk of severe disease due to COVID-19 than healthy peers. As social distancing measures continue during the COVID-19 pandemic, experts encourage individuals with underlying conditions to engage in telehealth appointments to maintain continuity of care while minimizing risk exposure. To date, however, little information has been provided regarding telehealth uptake among this high-risk population. OBJECTIVE: The aim of this study is to describe the telehealth use, resource needs, and information sources of individuals with chronic conditions during the COVID-19 pandemic. Secondary objectives include exploring differences in telehealth use by sociodemographic characteristics. METHODS: Data for this study were collected through an electronic survey distributed between May 12-14, 2020, to members of 26 online health communities for individuals with chronic disease. Descriptive statistics were run to explore telehealth use, support needs, and information sources, and z tests were run to assess differences in sociodemographic factors and information and support needs among those who did and did not use telehealth services. RESULTS: Among the 2210 respondents, 1073 (49%) reported engaging in telehealth in the past 4 months. Higher proportions of women engaged in telehealth than men (890/1781, 50% vs 181/424, 43%; P=.007), and a higher proportion of those earning household incomes of more than US $100,000 engaged in telehealth than those earning less than US $30,000 (195/370, 53% vs 241/530 45%; P=.003). Although 59% (133/244) of those younger than 40 years and 54% (263/486) of those aged 40-55 years used telehealth, aging populations were less likely to do so, with only 45% (677/1500) of individuals 56 years or older reporting telehealth use (P<.001 and P=.001, respectively). Patients with cystic fibrosis, lupus, and ankylosing spondylitis recorded the highest proportions of individuals using telehealth when compared to those with other diagnoses. Of the 2210 participants, 1333 (60%) participants either looked up information about the virus online or planned to in the future, and when asked what information or support would be most helpful right now, over half (1151/2210, 52%) responded "understanding how COVID-19 affects people with my health condition." CONCLUSIONS: Nearly half of the study sample reported participating in telehealth in the past 4 months. Future efforts to engage individuals with underlying medical conditions in telehealth should focus on outreach to men, members of lower-income households, and aging populations. These results may help inform and refine future health communications to further engage this at-risk population in telehealth as the pandemic continues.

Scoping review exploring the impact of digital systems on processes and outcomes in the care management of acute kidney injury and progress towards establishing learning healthcare systems.

OBJECTIVES: Digital systems have long been used to improve the quality and safety of care when managing acute kidney injury (AKI). The availability of digitised clinical data can also turn organisations and their networks into learning healthcare systems (LHSs) if used across all levels of health and care. This review explores the impact of digital systems i.e. on patients with AKI care, to gauge progress towards establishing LHSs and to identify existing gaps in the research. METHODS: Embase, PubMed, MEDLINE, Cochrane, Scopus and Web of Science databases were searched. Studies of real-time or near real-time digital AKI management systems which reported process and outcome measures were included. RESULTS: Thematic analysis of 43 studies showed that most interventions used real-time serum creatinine levels to trigger responses to enable risk prediction, early recognition of AKI or harm prevention by individual clinicians (micro level) or specialist teams (meso level). Interventions at system (macro level) were rare. There was limited evidence of change in outcomes. DISCUSSION: While the benefits of real-time digital clinical data at micro level for AKI management have been evident for some time, their application at meso and macro levels is emergent therefore limiting progress towards establishing LHSs. Lack of progress is due to digital maturity, system design, human factors and policy levers. CONCLUSION: Future approaches need to harness the potential of interoperability, data analytical advances and include multiple stakeholder perspectives to develop effective digital LHSs in order to gain benefits across the system.

The Evolution of Clinical Knowledge During COVID-19: Towards a Global Learning Health System.

OBJECTIVES: We examine the knowledge ecosystem of COVID-19, focusing on clinical knowledge and the role of health informatics as enabling technology. We argue for commitment to the model of a global learning health system to facilitate rapid knowledge translation supporting health care decision making in the face of emerging diseases. METHODS AND RESULTS: We frame the evolution of knowledge in the COVID-19 crisis in terms of learning theory, and present a view of what has occurred during the pandemic to rapidly derive and share knowledge as an (underdeveloped) instance of a global learning health system. We identify the key role of information technologies for electronic data capture and data sharing, computational modelling, evidence synthesis, and knowledge dissemination. We further highlight gaps in the system and barriers to full realisation of an efficient and effective global learning health system. CONCLUSIONS: The need for a global knowledge ecosystem supporting rapid learning from clinical practice has become more apparent than ever during the COVID-19 pandemic. Continued effort to realise the vision of a global learning health system, including establishing effective approaches to data governance and ethics to support the system, is imperative to enable continuous improvement in our clinical care.

The Role of a Resilient Information Infrastructure in COVID-19 Vaccine Uptake in Ontario.

The COVID-19 pandemic has highlighted the need for a robust and nimble public health data infrastructure. ICES - a government-sponsored, independent, non-profit research institute in Ontario, Canada - functions as a key component of a resilient information infrastructure and an enabler of data co-production, contributing to Ontario's response to the COVID-19 pandemic as part of a learning health system. Linked data on the cumulative incidence of infection and vaccination at the neighbourhood level revealed disparate uptake between areas with low versus high risk of COVID-19. These data were leveraged by the government, service providers, media and the public to inform a more efficient and equitable vaccination strategy.

Health information technology and digital innovation for national learning health and care systems.

Health information technology can support the development of national learning health and care systems, which can be defined as health and care systems that continuously use data-enabled infrastructure to support policy and planning, public health, and personalisation of care. The COVID-19 pandemic has offered an opportunity to assess how well equipped the UK is to leverage health information technology and apply the principles of a national learning health and care system in response to a major public health shock. With the experience acquired during the pandemic, each country within the UK should now re-evaluate their digital health and care strategies. After leaving the EU, UK countries now need to decide to what extent they wish to engage with European efforts to promote interoperability between electronic health records. Major priorities for strengthening health information technology in the UK include achieving the optimal balance between top-down and bottom-up implementation, improving usability and interoperability, developing capacity for handling, processing, and analysing data, addressing privacy and security concerns, and encouraging digital inclusivity. Current and future opportunities include integrating electronic health records across health and care providers, investing in health data science research, generating real-world data, developing artificial intelligence and robotics, and facilitating public-private partnerships. Many ethical challenges and unintended consequences of implementation of health information technology exist. To address these, there is a need to develop regulatory frameworks for the development, management, and procurement of artificial intelligence and health information technology systems, create public-private partnerships, and ethically and safely apply artificial intelligence in the National Health Service.