Implementation strategies and outcome measures for advancing learning health systems: a mixed methods systematic review
Bibliographic record
Abstract
Abstract Background Learning health systems strive to continuously integrate data and evidence into practice to improve patient outcomes and ensure value-based healthcare. While the LHS concept is gaining traction, the operationalization of LHSs is underexplored. Objective To identify and synthesize the existing evidence on the implementation and evaluation of advancing learning health systems across international health care settings. Methods A mixed methods systematic review was conducted. Six databases (CINAHL, Embase, Medline, PAIS, Scopus and Nursing at Allied Health Database) were searched up to July 2022 for terms related to learning health systems, implementation, and evaluation measures. Any study design, health care setting and population were considered for inclusion. No limitations were placed on language or date of publication. Two reviewers independently screened the titles, abstracts, and full texts of identified articles. Data were extracted and synthesized using a convergent integrated approach. Studies were critically appraised using relevant JBI critical appraisal checklists. Results Thirty-five studies were included in the review. Most studies were conducted in the United States (n = 21) and published between 2019 and 2022 (n = 24). Digital data capture was the most common LHS characteristic reported across studies, while patient engagement, aligned governance and a culture of rapid learning and improvement were reported least often. We identified 33 unique strategies for implementing LHSs including: change record systems, conduct local consensus discussions and audit & provide feedback. A triangulation of quantitative and qualitative data revealed three integrated findings related to the implementation of LHSs: (1) The digital infrastructure of LHSs optimizes health service delivery; (2) LHSs have a positive impact on patient care and health outcomes; and (3) LHSs can influence health care providers and the health system. Conclusion This paper provides a comprehensive overview of the implementation of LHSs in various healthcare settings. While this review identified key implementation strategies, potential outcome measures, and components of functioning LHSs, further research is needed to better understand the impact of LHSs on patient, provider and population outcomes, and health system costs. Health systems researchers should continue to apply the LHS concept in practice, with a stronger focus on evaluation.
Stored with the screening record, where it is evidence for the labels above.
How this classification was reachedexpand
The three-model screen
all 5,600 screened works →All three models called this out of scope.
Systematic review of how learning health systems are implemented and evaluated; the object is health system practice rather than research practice, though evidence use makes it a boundary case.
The review studies implementation of learning health systems for healthcare delivery, not research practice itself.
Systematic review of learning health system implementation in care delivery; uses synthesis methods to answer a health-systems question.
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.133 | 0.280 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.015 | 0.017 |
| Bibliometrics | 0.025 | 0.026 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.010 | 0.008 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".