Integrating Prevention into Routine Clinical Workflows in Alberta, Canada through a Learning Health System Approach: Early Lessons Learned
Bibliographic record
Abstract
Background: We present lessons from the Integrating Prevention into Health (IPiC-Health) initiative as a rapid LHS in complex clinical settings, aimed at improving the population health and well-being through preventive care. Approach: The IPiC-health project builds a rapid LHS for preventive care, leveraging health information technology to promote measurable change for improving population health and wellness; integrating screening, brief intervention and referral (SBIR) for modifiable risk factors into Connect Care - Alberta province-wide Electronic Health Record (EHR). This interventional research project utilizes mixed methods (pragmatic trial and qualitative assessment) for implementation and effectiveness research. As an important part of the LHS, we co-create and integrate clinical workflows, create rapid feedback mechanisms for improving care, and study effectiveness of integrating SBIR on patient outcomes, while capturing provider and patient perspectives. Results: We identified and engaged key partners, multi-disciplinary experts and site champions for co-designing clinical workflows, including Alberta Health Services leadership, clinical and academic sites. Leadership at eight clinical sites (5 ambulatory, 3 inpatient) agreed to the importance and implementation of SBIR.Embedded Research Coordinators/staff played a critical role in formalizing assessing readiness, patient recruitment, creating champions and clinical workflows in close consultation with clinical teams. Readiness assessments helped tailor training and support SBIR integration into clinical and EHR workflows. Control group recruitment followed with 238 participants; 644 high or medium risk for at least one risk factor (smoking, alcohol use, physical inactivity); recruited by December 2023 at 3 sites, while currently 2 sites have started the implementation phase.Towards operationalizing the LHS, we employ mixed methods (EHR data, patient and clinician semi-structured interviews, clinician observation), to identify challenges, and create feedback reports for reflection, motivation, and improvement at clinical sites. Identified challenges and barriers are recorded and resolved using the Consolidated Framework for Implementation Research.Important lessons learnt during the project initial phase include limitations in the current EHR offering, such as fragmented documentation for preventive care; tools not aligned to care delivery in Alberta; different interfaces for different providers; problems accessing the SBIR domains for charting; lack of or duplicated fields leading to inconsistent data recording; and lack of linkages to referral related provincial programs, such as Alberta Quits. Implications: Preventive care is an oft-overlooked aspect within the care continuum. We are co-creating standardized clinical workflow at sites for integrating SBIR in routine care, while offering on-ground support to clinical teams. This will be helpful towards promoting longer term sustainability for improving SBIR in routine care. We are also initiating patient surveys for gauging the effectiveness of SBIR in behavior change.While providers view SBIR for modifiable risk factors as important, Connect Care workflow optimization, motivation and continued education are key concerns for longer-term uptake and use of the LHS for preventive care.
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 | 0.020 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.012 | 0.005 |
| Scholarly communication | 0.006 | 0.002 |
| Open science | 0.006 | 0.006 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".