Prevention and Early Delirium Identification Carer Toolkit ( <scp>PREDICT</scp> ): A Study Protocol for a Stepped‐Wedge, Cluster Randomised Controlled Trial
Bibliographic record
Abstract
BACKGROUND: Delirium, a common, serious and often preventable complication in older hospitalised adults, contributes to significant health and social care costs. Carers are uniquely positioned to identify early signs and support delirium prevention. The Prevention & Early Delirium Identification Carer Toolkit (PREDICT), a novel model of care designed to educate carers about delirium management and prevention strategies, enables them to actively participate in the care and recovery of their person. Developed through a comprehensive literature review, a co-designed eDelphi and pilot study, PREDICT demonstrated acceptability and feasibility. AIMS: To evaluate the effectiveness, implementation and cost-benefit of a PREDICT in hospital settings. METHOD: A stepped-wedge cluster randomised controlled trial (SW-cRCT), consisting of a cohort study, healthcare service evaluation, and process evaluation. The study will assess carer and staff knowledge of delirium, carer care giving stress, health service outcomes (e.g., incidence, length of stay, readmissions) and cost-benefit. DISCUSSION: PREDICT is a scalable, person-centred approach that supports both patients and carers, with the potential to embed best-practice delirium management into routine healthcare. PUBLIC AND PATIENT INVOLVEMENT: This study was developed in consultation with older adults, carers and healthcare staff. Two consumer representatives joined the project steering committee and contributed to shaping the research question, refining the study protocol and selecting outcome measures relevant to families and healthcare staff. Carers were involved in reviewing participant information sheets and the PREDICT website, providing feedback to ensure clarity and accessibility. Results will be shared with participants and the wider community through plain-language summaries and public presentations. TRIAL REGISTRATION: Australian and New Zealand Clinical trial: ACTRN12625000705482 registered on the 3rd of July 2025.
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 | 0.080 | 0.084 |
| Meta-epidemiology (narrow) | 0.007 | 0.004 |
| Meta-epidemiology (broad) | 0.013 | 0.007 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.004 | 0.005 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.005 | 0.003 |
| Research integrity | 0.010 | 0.009 |
| Insufficient payload (model declined to judge) | 0.090 | 0.017 |
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".