Evaluating learning health systems: a jurisdictional scan
Bibliographic record
Abstract
The Learning Health System (LHS) aims to improve healthcare by using continuous data analysis to create equitable, patient-centered, and cost-effective care. Evaluating LHS success is challenging due to real-world variability in execution and implementation and absence of clear metrics. We conducted an international jurisdictional scan to highlight common evaluation approaches, indicators, outcomes, challenges, and assumptions related to establishing counterfactuals in LHS evaluation. Evaluation outputs were categorized into four types: description, lessons learned, efficacy, and effectiveness. Frequencies and thematic analysis were used to describe LHSs, their evaluations, indicators of change, and lessons learned. 45 papers describing 44 LHSs were included. 30 papers shared lessons on LHS progress, 14 reported on efficacy during scaling, and none reported on effectiveness of sustained systems. Ingredients perceived to contribute to a successful LHS included engagement of key individuals, establishment of a LHS culture, data considerations, and contextual factors. Future evaluations should consider LHS maturity, utilize counterfactuals, and prioritize equity. Evaluating and addressing these gaps can fuel LHS effectiveness and ensure that diverse needs of patients and providers are met. Ultimately, structured and more standardized evaluation efforts could foster a culture of continuous learning and improvement, enabling health systems to better enhance population health outcomes and deliver high-quality, equitable care. • LHS evaluations varied by maturity, ranging from system description to lessons, efficacy, and effectiveness • Key ingredients for LHS success: engaged people, supportive culture, strong data, and context • There was limited focus on equity and minimal mention of counterfactuals in the approaches used to conduct LHS evaluations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
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 | 0.304 | 0.485 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.005 |
| Bibliometrics | 0.033 | 0.042 |
| Science and technology studies | 0.004 | 0.008 |
| Scholarly communication | 0.015 | 0.011 |
| Open science | 0.007 | 0.018 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.013 | 0.001 |
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".