Advancing a learning health system through biomedical and health informatics

A Learning Health System (LHS) is one “in which science, informatics, incentives, and culture are aligned for continuous improvement and innovation, with best practices seamlessly embedded in the delivery process and new knowledge captured as an integral by-product of the delivery experience.”¹ For almost 2 decades, there has been a clear recognition of the criticality of informatics infrastructure, technologies, and processes as the underpinning of an LHS.² The Journal of the American Medical Informatics Association (JAMIA) has been a premier venue for publishing on the topic. For example, the April 2014 issue included multiple papers that described scalable infrastructure for an LHS.^3–5 A 2015 paper by Friedman et al. reported on a National Science Foundation workshop that resulted in a research agenda for the high-functioning LHS and called for an interdisciplinary science of learning systems.⁶

Despite some progress toward an LHS, in a Perspective in this issue, Gunderson, Embi, Friedman, and Melton argue that the informatics community has been relatively slow to formalize LHS as a priority area.⁷ To generate informatics priorities for an LHS, they compiled results from a short survey of LHS leaders and American Medical Informatics Association (AMIA) members, discussion from an LHS reception at the AMIA annual meeting, and a follow-up survey to inform priorities at the intersection of LHS and informatics. Through a thematic analysis, the authors identified 7 opportunities at the intersection of LHS and informatics: Understanding and Context, Shared Resources, Collaboration, LHS Education, Data and Data Exchange, Demonstration and Evaluation, and Patient Centeredness (ie, inclusion of patient voices). They also identified immediate LHS informatics priorities: (1) establish informatics LHS forum(s); (2) disseminate case reports of LHS informatics successes and failures; (3) create LHS informatics education resources; and (4) advance understanding of LHS principles in informatics.

The 4 additional papers highlighted in this editorial reflect several opportunities delineated by Gunderson et al.⁷ Two papers focus on data exchange and interoperability.^8,9 Within the context of the Rhode Island Quality Institute, which operates the statewide health information exchange (HIE), Eisman et al. explored the potential for a centrally managed HIE standardized to a common data model (CDM), that is, the Observational Medical Outcomes Partnership (OMOP) CDM, to facilitate semantic data flow needed to support an LHS.⁸ Using the example of atherosclerotic cardiovascular disease (ASCVD) risk and primary prevention practices, they calculated longitudinal 10-year ASCVD risk on 62 999 individuals of whom almost two-thirds had ASCD risk factors from more than one data partner. They also demonstrated the ability of their approach for granular tracking of individual ASCVD risk, primary prevention strategies (ie, statin therapy), and incident disease thus providing the informatics foundation for intervention development within an LHS. Everson and Richwine used 2023 nationally representative survey data on US hospitals (N = 2420) to examine major and minor barriers to HIE across organizations, and how barriers vary by hospital characteristics and methods used for HIE.⁹ They found that most hospitals experienced at least one minor or major barrier to HIE, with the most common major barriers relating to different vendors and capabilities of HIE partners. The prevalence of barriers varied by hospital type and methods used for HIE, with barriers more often preventing HIE for lower-resourced hospitals and those using outdated HIE methods.

There is increasing recognition that health-related social needs (HRSN) data are an essential component of an LHS. Richwine et al. explored variation in routine and structured collection and use of HRSN data through analysis of nationally representative survey data on US hospitals (N = 2775).¹⁰ They found that 88% of hospitals collected HRSN data but fewer collected it routinely (64%) or in structured format (72%). While 79% of hospitals commonly used HRSN data for internal purposes (eg, discharge planning), those that collected data routinely and in a structured format also used data for coordination or HIE with other organizations (eg, referrals). Hospital location, ownership, system-affiliation, value-based care participation, and critical access designation were associated with HRSN data collection, but only system-affiliation was consistently and positively associated with data use. Routine and structured collection of HRSN data is a foundation for not only supporting patient care but also improving community and population health.

Digital quality measures (dQMs) are an important component of an LHS, yet little is known about how dQMs function at scale. In a Brief Communication, Zimolzak and colleagues report on the application of a previously validated dQM (emergency encounter followed by new lung cancer diagnosis within 30 days) to Epic Cosmos, a deidentified database covering 184 million US patients.¹¹ Through examining the relationship between the dQM and sociodemographic factors, they found that emergency presentation rate was higher in patients who identified as Black as compared to White, lived in a lower-income ZIP code, self-reported transport difficulties, and were younger and more socially vulnerable, These findings demonstrate the successful application of a dQM to the largest US EHR database. Furthermore, the authors suggest that this dQM could be a marker for sociodemographic vulnerabilities in lung cancer diagnosis.

Thirty years ago, JAMIA published a paper in which I envisioned some of the informatics foundation for what we now call LHS.¹² Research at the intersection of LHS and biomedical and health informatics remains a key area of interest for the journal. The Perspective by Gunderson et al offers direction on informatics priorities related to LHS and a call to action for informaticians. We look forward to receiving innovative and rigorous work that is responsive to this call to action.

Funding

None declared.

Conflicts of interest

None declared.

Data availability

Not applicable.

References