A holistic approach to integrating patient, family, and lived experience voices in the development of the BrainHealth Databank: a digital learning health system to enable artificial intelligence in the clinic
Bibliographic record
Abstract
Artificial intelligence, machine learning, and digital health innovations have tremendous potential to advance patient-centred, data-driven mental healthcare. To enable the clinical application of such innovations, the Krembil Centre for Neuroinformatics at the Centre for Addiction and Mental Health, Canada's largest mental health hospital, embarked on a journey to co-create a digital learning health system called the BrainHealth Databank (BHDB). Working with clinicians, scientists, and administrators alongside patients, families, and persons with lived experience (PFLE), this hospital-wide team has adopted a systems approach that integrates clinical and research data and practices to improve care and accelerate research. PFLE engagement was intentional and initiated at the conception stage of the BHDB to help ensure the initiative would achieve its goal of understanding the community's needs while improving patient care and experience. The BHDB team implemented an evolving, dynamic strategy to support continuous and active PFLE engagement in all aspects of the BHDB that has and will continue to impact patients and families directly. We describe PFLE consultation, co-design, and partnership in various BHDB activities and projects. In all three examples, we discuss the factors contributing to successful PFLE engagement, share lessons learned, and highlight areas for growth and improvement. By sharing how the BHDB navigated and fostered PFLE engagement, we hope to motivate and inspire the health informatics community to collectively chart their paths in PFLE engagement to support advancements in digital health and artificial intelligence.
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 | 0.048 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.019 | 0.024 |
| Scholarly communication | 0.024 | 0.023 |
| Open science | 0.004 | 0.044 |
| Research integrity | 0.005 | 0.015 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".