Implementing learning health systems in the UK NHS: Policy actions to improve collaboration and transparency and support innovation and better use of analytics

Leveraging data to support health equity in an integrated delivery and finance system

Introduction

To accelerate healthcare transformation and advance health equity, scientists in learning health systems (LHSs) require ready access to integrated, comprehensive data that includes information on social determinants of health (SDOH).

Methods

We describe how an integrated delivery and finance system leveraged its learning ecosystem to advance health equity through (a) a cross-sector initiative to integrate healthcare and human services data for better meeting clients' holistic needs and (b) a system-level initiative to collect and use patient-reported SDOH data for connecting patients to needed resources.

Results

Through these initiatives, we strengthened our health system's capacity to meet diverse patient needs, address health disparities, and improve health outcomes. By sharing and integrating healthcare and human services data, we identified 281 000 Shared Services Clients and enhanced care management for 100 adult Medicaid/Special Needs Plan members. Over a 1-year period, we screened 9173 (37%) patients across UPMC's Women's Health Services Line and connected over 700 individuals to social services and supports.

Conclusions

Opportunities exist for LHSs to improve, expand, and sustain their innovative data practices. As learnings continue to emerge, LHSs will be well positioned to accelerate healthcare transformation and advance health equity.

Diagnosing an overcrowded emergency department from its Electronic Health Records

Emergency department overcrowding is a complex problem that persists globally. Data of visits constitute an opportunity to understand its dynamics. However, the gap between the collected information and the real-life clinical processes, and the lack of a whole-system perspective, still constitute a relevant limitation. An analytical pipeline was developed to analyse one-year of production data following the patients that came from the ED (n = 49,938) at Uppsala University Hospital (Uppsala, Sweden) by involving clinical experts in all the steps of the analysis. The key internal issues to the ED were the high volume of generic or non-specific diagnoses from non-urgent visits, and the delayed decision regarding hospital admission caused by several imaging assessments and lack of hospital beds. Furthermore, the external pressure of high frequent re-visits of geriatric, psychiatric, and patients with unspecified diagnoses dramatically contributed to the overcrowding. Our work demonstrates that through analysis of production data of the ED patient flow and participation of clinical experts in the pipeline, it was possible to identify systemic issues and directions for solutions. A critical factor was to take a whole systems perspective, as it opened the scope to the boundary effects of inflow and outflow in the whole healthcare system.

eHealth implementation in Europe: a scoping review on legal, ethical, financial, and technological aspects

Background

The evolution of eHealth development has shifted from standalone tools to comprehensive digital health environments, fostering data exchange among diverse stakeholders and systems. Nevertheless, existing research and implementation frameworks have primarily emphasized technological and organizational aspects of eHealth implementation, overlooking the intricate legal, ethical, and financial considerations. It is essential to discover what legal, ethical, financial, and technological challenges should be considered to ensure successful and sustainable implementation of eHealth.

Objective

This review aims to provide insights into barriers and facilitators of legal, ethical, financial, and technological aspects for successful implementation of complex eHealth technologies, which impacts multiple levels and multiple stakeholders.

Methods

A scoping review was conducted by querying PubMed, Scopus, Web of Science, and ACM Digital Library (2018-2023) for studies describing the implementation process of eHealth technologies that facilitate data exchange. Studies solely reporting clinical outcomes or conducted outside Europe were excluded. Two independent reviewers selected the studies. A conceptual framework was constructed through axial and inductive coding, extracting data from literature on legal, ethical, financial, and technological aspects of eHealth implementation. This framework guided systematic extraction and interpretation.

Results

The search resulted in 7.308 studies that were screened for eligibility, of which 35 (0.48%) were included. Legal barriers revolve around data confidentiality and security, necessitating clear regulatory guidelines. Ethical barriers span consent, responsibility, liability, and validation complexities, necessitating robust frameworks. Financial barriers stem from inadequate funding, requiring (commercial) partnerships and business models. Technological issues include interoperability, integration, and malfunctioning, necessitating strategies for enhancing data reliability, improving accessibility, and aligning eHealth technology with existing systems for smoother integration.

Conclusions

This research highlights the multifaceted nature of eHealth implementation, encompassing legal, ethical, financial, and technological considerations. Collaborative stakeholder engagement is paramount for effective decision-making and aligns with the transition from standalone eHealth tools to integrated digital health environments. Identifying suitable stakeholders and recognizing their stakes and values enriches implementation strategies with expertise and guidance across all aspects. Future research should explore the timing of these considerations and practical solutions for regulatory compliance, funding, navigation of responsibility and liability, and business models for reimbursement strategies.

An initial typology of approaches used by policy and practice agencies to achieve sustained implementation of interventions to improve health

BACKGROUND

Scientific investigation of how to sustain the implementation of evidence-based interventions (EBI) is emerging. Sustaining the implementation of EBIs helps ensure their effects on improving health endure. External policy or practice agencies, such as government health departments, are often tasked with supporting individual organisations with sustaining their delivery of EBIs, for example, through financing, training or the provision of other supports. However, to our knowledge, the approaches taken by policy and practice agencies to support the sustainment of EBIs have not been consolidated, categorised and described as a typology.

MAIN BODY

To improve conceptual clarity and support both research and practice, we developed an initial working typology of the practical approaches to sustain implementation of EBIs (i.e. sustainment) in order to improve long term health from the perspective of these agencies. The working typology includes three broad approaches. The first, termed 'Self-Sustainment', is when implementation of the EBI by an organisation (e.g. hospital, clinic, school) is expected to continue (sustain) in the absence of external (agency) support. The second, termed 'Static Sustainment Support', involves the provision of pre-defined external (agency) support to assist organisations to continue implementation of an EBI. The final approach is termed 'Dynamic Sustainment Support', whereby support provided by an external agency is dynamic (continues to be adapted) overtime to assist organisations continue implementation of an intervention which may itself also evolve.

CONCLUSIONS

We describe the contexts and circumstances where each may be most appropriate in achieving sustained implementation and discuss their research and practice implications.

Defining the Learning Health Care System: An International Health System Leadership Perspective

PURPOSE

Over the past 2 decades, many academic health centers (AHCs) have implemented learning health systems (LHSs). However, the LHS has been defined with limited input from AHC leaders. This has implications because these individuals play a critical role in LHS implementation and sustainability. This study aims to demonstrate how an international group of AHC leaders defines the LHS, and to identify key considerations they would pose to their leadership teams to implement and sustain the LHS.

METHOD

A semistructured survey was developed and administered in 2022 to members of the Association of Academic Health Centers President's Council on the Learning Health System to explore how AHC leaders define the LHS in relation to their leadership roles. The authors then conducted a focus group, informed by the survey, with these leaders. The focus group was structured using the nominal group technique to facilitate consensus on an LHS definition and key considerations. The authors mapped the findings to an existing LHS framework, which includes 7 components: organizational, performance, ethics and security, scientific, information technology, data, and patient outcomes.

RESULTS

Thirteen AHC leaders (100%) completed the survey and 10 participated in the focus group. The AHC leaders developed the following LHS definition: "A learning health system is a health care system in which clinical and care-related data are systematically integrated to catalyze discovery and implementation of new knowledge that benefits patients, the community, and the organization through improved outcomes." The key considerations mapped to all LHS framework components, but participants also described as important the ability to communicate the LHS concept and be able to rapidly adjust to unforeseen circumstances.

CONCLUSIONS

The LHS definition and considerations developed in this study provide a shared foundation and road map for future discussions among leaders of AHCs interested in implementing and sustaining an LHS.

Health Information Exchange: Understanding the Policy Landscape and Future of Data Interoperability

OBJECTIVES

To review recent literature on health information exchange (HIE), focusing on the policy approach of five case study nations: the United States of America, the United Kingdom, Germany, Israel, and Portugal, as well as synthesize lessons learned across countries and provide recommendations for future research.

METHODS

A narrative review of each nation's HIE policy frameworks, current state, and future HIE strategy.

RESULTS

Key themes that emerged include the importance of both central decision-making as well as local innovation, the multiple and complex challenges of broad HIE adoption, and the varying role of HIE across different national health system structures.

CONCLUSION

HIE is an increasingly important capability and policy priority as electronic health record (EHR) adoption becomes more common and care delivery is increasingly digitized. While all five case study nations have adopted some level of HIE, there are significant differences across their level of data sharing infrastructure and maturity, and each nation took a different policy approach. While identifying generalizable strategies across disparate international systems is challenging, there are several common themes across successful HIE policy frameworks, such as the importance of central government prioritization of data sharing. Finally, we make several recommendations for future research to expand the breadth and depth of the literature on HIE and guide future decision-making by policymakers and practitioners.

Clinical deployment environments: Five pillars of translational machine learning for health

Machine Learning for Health (ML4H) has demonstrated efficacy in computer imaging and other self-contained digital workflows, but has failed to substantially impact routine clinical care. This is no longer because of poor adoption of Electronic Health Records Systems (EHRS), but because ML4H needs an infrastructure for development, deployment and evaluation within the healthcare institution. In this paper, we propose a design pattern called a Clinical Deployment Environment (CDE). We sketch the five pillars of the CDE: (1) real world development supported by live data where ML4H teams can iteratively build and test at the bedside (2) an ML-Ops platform that brings the rigour and standards of continuous deployment to ML4H (3) design and supervision by those with expertise in AI safety (4) the methods of implementation science that enable the algorithmic insights to influence the behaviour of clinicians and patients and (5) continuous evaluation that uses randomisation to avoid bias but in an agile manner. The CDE is intended to answer the same requirements that bio-medicine articulated in establishing the translational medicine domain. It envisions a transition from "real-world" data to "real-world" development.

Predicting Risk of Hospital Admission in Patients With Suspected COVID-19 in a Community Setting: Protocol for Development and Validation of a Multivariate Risk Prediction Tool

Background

During the pandemic, remote consultations have become the norm for assessing patients with signs and symptoms of COVID-19 to decrease the risk of transmission. This has intensified the clinical uncertainty already experienced by primary care clinicians when assessing patients with suspected COVID-19 and has prompted the use of risk prediction scores, such as the National Early Warning Score (NEWS2), to assess severity and guide treatment. However, the risk prediction tools available have not been validated in a community setting and are not designed to capture the idiosyncrasies of COVID-19 infection.

Objective

The objective of this study is to produce a multivariate risk prediction tool, RECAP-V1 (Remote COVID-19 Assessment in Primary Care), to support primary care clinicians in the identification of those patients with COVID-19 that are at higher risk of deterioration and facilitate the early escalation of their treatment with the aim of improving patient outcomes.

Methods

The study follows a prospective cohort observational design, whereby patients presenting in primary care with signs and symptoms suggestive of COVID-19 will be followed and their data linked to hospital outcomes (hospital admission and death). Data collection will be carried out by primary care clinicians in four arms: North West London Clinical Commissioning Groups (NWL CCGs), Oxford-Royal College of General Practitioners (RCGP) Research and Surveillance Centre (RSC), Covid Clinical Assessment Service (CCAS), and South East London CCGs (Doctaly platform). The study involves the use of an electronic template that incorporates a list of items (known as RECAP-V0) thought to be associated with disease outcome according to previous qualitative work. Data collected will be linked to patient outcomes in highly secure environments. We will then use multivariate logistic regression analyses for model development and validation.

Results

Recruitment of participants started in October 2020. Initially, only the NWL CCGs and RCGP RSC arms were active. As of March 24, 2021, we have recruited a combined sample of 3827 participants in these two arms. CCAS and Doctaly joined the study in February 2021, with CCAS starting the recruitment process on March 15, 2021. The first part of the analysis (RECAP-V1 model development) is planned to start in April 2021 using the first half of the NWL CCGs and RCGP RSC combined data set. Posteriorly, the model will be validated with the rest of the NWL CCGs and RCGP RSC data as well as the CCAS and Doctaly data sets. The study was approved by the Research Ethics Committee on May 27, 2020 (Integrated Research Application System number: 283024, Research Ethics Committee reference number: 20/NW/0266) and badged as National Institute of Health Research Urgent Public Health Study on October 14, 2020.

Conclusions

We believe the validated RECAP-V1 early warning score will be a valuable tool for the assessment of severity in patients with suspected COVID-19 in the community, either in face-to-face or remote consultations, and will facilitate the timely escalation of treatment with the potential to improve patient outcomes.

Trial Registration

ISRCTN registry ISRCTN13953727; https://www.isrctn.com/ISRCTN13953727

International Registered Report Identifier (IRRID)

DERR1-10.2196/29072

Impact of a wound management system on budget optimisation, formulary compliance and variations in care

Optimising budgets in wound care is crucial if local health economy efficiencies are to be realised. How spending is managed and monitored can be difficult for community nursing services due to the variety of supply routes. Online wound management systems not on help tailor supply routes to reduce waste, thereby reducing cost, but also provide an audit platform for transparency across clinical practice. The non-prescription ordering system Formeo was implemented across City Health Care Partnership (CHCP), Hull, through a value-based industry collaboration. With its use, monthly spend on wound care reduced by approximately £5354 (11.9%), with a reduction in the total spend of £64 254. Further, Formeo enabled an audit of clinical practice to minimise products on the formulary. This provided CHCP, Hull, the opportunity to reduce variations in care, and therefore potentially improve clinical outcomes.

Learning health systems using data to drive healthcare improvement and impact: a systematic review

Background

The transition to electronic health records offers the potential for big data to drive the next frontier in healthcare improvement. Yet there are multiple barriers to harnessing the power of data. The Learning Health System (LHS) has emerged as a model to overcome these barriers, yet there remains limited evidence of impact on delivery or outcomes of healthcare.

Objective

To gather evidence on the effects of LHS data hubs or aligned models that use data to deliver healthcare improvement and impact. Any reported impact on the process, delivery or outcomes of healthcare was captured.

Methods

Systematic review from CINAHL, EMBASE, MEDLINE, Medline in-process and Web of Science PubMed databases, using learning health system, data hub, data-driven, ehealth, informatics, collaborations, partnerships, and translation terms. English-language, peer-reviewed literature published between January 2014 and Sept 2019 was captured, supplemented by a grey literature search. Eligibility criteria included studies of LHS data hubs that reported research translation leading to health impact.

Results

Overall, 1076 titles were identified, with 43 eligible studies, across 23 LHS environments. Most LHS environments were in the United States (n = 18) with others in Canada, UK, Sweden and Australia/NZ. Five (21.7%) produced medium-high level of evidence, which were peer-reviewed publications.

Conclusions

LHS environments are producing impact across multiple continents and settings.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-021-06215-8.

The three numbers you need to know about healthcare: the 60-30-10 Challenge

BACKGROUND

Healthcare represents a paradox. While change is everywhere, performance has flatlined: 60% of care on average is in line with evidence- or consensus-based guidelines, 30% is some form of waste or of low value, and 10% is harm. The 60-30-10 Challenge has persisted for three decades.

MAIN BODY

Current top-down or chain-logic strategies to address this problem, based essentially on linear models of change and relying on policies, hierarchies, and standardisation, have proven insufficient. Instead, we need to marry ideas drawn from complexity science and continuous improvement with proposals for creating a deep learning health system. This dynamic learning model has the potential to assemble relevant information including patients' histories, and clinical, patient, laboratory, and cost data for improved decision-making in real time, or close to real time. If we get it right, the learning health system will contribute to care being more evidence-based and less wasteful and harmful. It will need a purpose-designed digital backbone and infrastructure, apply artificial intelligence to support diagnosis and treatment options, harness genomic and other new data types, and create informed discussions of options between patients, families, and clinicians. While there will be many variants of the model, learning health systems will need to spread, and be encouraged to do so, principally through diffusion of innovation models and local adaptations.

CONCLUSION

Deep learning systems can enable us to better exploit expanding health datasets including traditional and newer forms of big and smaller-scale data, e.g. genomics and cost information, and incorporate patient preferences into decision-making. As we envisage it, a deep learning system will support healthcare's desire to continually improve, and make gains on the 60-30-10 dimensions. All modern health systems are awash with data, but it is only recently that we have been able to bring this together, operationalised, and turned into useful information by which to make more intelligent, timely decisions than in the past.