A Rapid Learning Health System to Support Implementation of Early Intervention Services for Psychosis in Quebec, Canada: Study Protocol
Bibliographic record
Abstract
Abstract Background: Given the strong evidence for their effectiveness, early intervention services for psychosis (EIS) are being widely implemented. However, heterogeneity in the implementation of essential components, remains an ongoing challenge. Rapid learning health systems (RLHS), that embed data collection in clinical settings for real-time learning and continual quality improvement, can address this challenge. We therefore implemented a RLHS in 11 EIS in Quebec, Canada. This project aims to determine the feasibility and acceptability of implementing a RLHS in EIS, and to assess its impact on compliance with standards for essential EIS components. Methods: Following literature recommendations, the implementation of this RLHS involves six iterative phases: external and internal scan, design, implementation, evaluation, adjustment, and dissemination. Multiple stakeholder groups (service users, families, clinicians, researchers, decision makers, provincial EIS association) are involved in all phases. Meaningful indicators of EIS quality (e.g., satisfaction, timeliness of response to referrals) were selected based on literature review, provincial guidelines, and stakeholder consensus on indicators prioritisation. A digital infrastructure was designed and deployed that comprises (a) a user-friendly interface for routinely collecting data from programs (b) a digital terminal and mobile app to collect feedback from service users and families regarding care received, health, and quality of life (c) data analytic, visualization and reporting functionalities to provide participating programs with real-time feedback on their performance over time, and in relation to standards and to other programs, along with tailored recommendations. Community of practice activities are being conducted that leverage insights from data to build capacity among programs to continually progress towards aligning their practice with standards/best practices. Guided by the RE-AIM framework, we are collecting quantitative and qualitative data on the Reach, Effectiveness Adoption, Implementation and Maintenance of our RLHS. These RE-AIM data will be analyzed to evaluate our RLHS’s impacts. Discussion: This project will yield valuable insights about how a RLHS can be implemented by EIS, along with preliminary evidence for its acceptability, feasibility and impacts on program-level outcomes. Its findings will refine our RLHS further and advance approaches that bring data, stakeholder voices and collaborative learning to improve outcomes and service quality in psychosis. Trial registration: NA
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 | 0.028 | 0.019 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.003 |
| Bibliometrics | 0.003 | 0.005 |
| Science and technology studies | 0.009 | 0.003 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.049 | 0.006 |
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".