T245. A MODEL 2.0 FOR EARLY INTERVENTION SERVICES FOR PSYCHOSIS: USING A LEARNING HEALTHCARE SYSTEM APPROACH TO IMPROVE EVIDENCE-BASED CARE
Bibliographic record
Abstract
Abstract Background In Canada, 26.3% of people reporting having mental disorders have indicated that they did not receive adequate care for their mental illness. However, early and evidence-based treatment can significantly reduce the severity of mental illnesses. Early Intervention Services (EIS) for psychosis are an example of such an intervention. EIS are widely recognized as a more effective treatment than routine care for early psychosis. Most Canadian EIS for psychosis follow recommendations on clinical components of care (i.e., easy and rapid access, a case management team approach); however, evidence-based interventions (e.g., measurement-based care or integrated psychosocial interventions) are not always available. Overall, various barriers limit the provision of quality care in the mental health sector, including EIS for psychosis treatment. These barriers include insufficient funding at a time of increasing demand; lack of services; lack of evidence- and measurement-based treatments; and insufficient training for staff and resources for patients. Innovative solutions are required. This presentation describes how e-mental health (eMH) technologies can mitigate these barriers, thus increasing access to evidence-based treatments. Methods Using a learning healthcare system approach, this 2.0 mental health services model aims to (a) identify, describe, and explain the factors affecting the routine incorporation and sustainability of eMH technologies in EIS for psychosis, and (b) optimize the methods associated with the development, adaptation, and evaluation of eMH technologies in real clinical settings. These aims are achieved by implementing three e-MH projects and unpacking the co-design/adaptation process and test the implementation, evaluation, and sustainability of eMH interventions and their effects on patient outcomes. Results The learning healthcare system is considered a new research paradigm able to promote quality, safety, and value in health care. Three project are at the core of this learning healthcare system for psychosis: (1) e-Mental Health Assessment and Monitoring (Project A: DIALOG+/e-Pathways to care): (a) To promote evidence- and measurement-based care in EIS for psychosis and (b) to use such technologies (such as electronic data capture platforms and data visualization) to support shared decision-making during treatment; (2) e-Treatment (Project B: CBT/pathways to care game-based interviews): (a) To facilitate the access and use of e-cognitive behavioral therapy (e-CBT) interventions in EIS for psychosis and (b) to support the treatment of secondary illnesses/comorbidities (depression and anxiety); (3) Web-based Training (Project C e-Training): (a) To co-produce web-based training and evaluate its effects on building capacity for the use of eMH technologies in EIS for psychosis and (b) to deliver psycho-educational interventions and continuing education training through interactive case-based learning. Discussion This work is timely. The innovative use of the rapid learning system approach in EIS for psychosis will offer a unique opportunity for integrating technologies and data into clinical practice, and should bring meaningful benefits to patients and promote Quebec’s open science research.
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 | 0.027 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.007 | 0.004 |
| Open science | 0.003 | 0.009 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.022 | 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; 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".