Data-Driven Decision Support Tool Co-Development with a Primary Health Care Practice Based Learning Network
Bibliographic record
Abstract
Background: The Alliance for Healthier Communities is a learning health system that supports Community Health Centres (CHCs) across Ontario, Canada to provide team-based primary health care to people who otherwise experience barriers to care. This case study describes the ongoing process and lessons learned from the first Alliance for Healthier Communities' Practice Based Learning Network (PBLN) data-driven decision support tool co-development project. Methods: We employ an iterative approach to problem identification and methods development for the decision support tool, moving between discussion sessions and case studies with CHC electronic health record (EHR) data. We summarize our work to date in terms of six stages: population-level descriptive-exploratory study, PBLN team engagement, decision support tool problem selection, sandbox case study 1: individual-level risk predictions, sandbox case study 2: population-level planning predictions, project recap and next steps decision. Results: The population-level study provided an initial point of engagement to consider how clients are (not) represented in EHR data and to inform problem selection and methodological decisions thereafter. We identified three initial meaningful types of decision support, with target application areas: risk prediction/screening, triaging specialized program referrals, and identifying care access needs. Based on feasibility and expected impact, we started with the goal to support earlier identification of mental health decline after diabetes diagnosis. As discussions deepened around clinical use cases associated with example prediction task set ups, the target problem evolved towards supporting the upstream task of organizational planning and advocacy for adequate mental health care service capacity to meet incoming needs. Conclusions: This case study contributes towards a tool to support diabetes and mental health care, as well as lays groundwork for future CHC EHR-based decision support tool initiatives. We share lessons learned and reflections from our process that other primary health care organizations may use to inform their own co-development initiatives while we continue to work on advancing the population-level capacity planning model.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.024 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.003 | 0.009 |
| Research integrity | 0.001 | 0.009 |
| Insufficient payload (model declined to judge) | 0.002 | 0.005 |
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; both teacher heads agree on what is shown here.
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".