Using routinely collected data to develop and evaluate a clinical tool for early identification of palliative care needs in long-term care: The RESPECT Project.
Bibliographic record
Abstract
ObjectivesPrognostication tools reporting personalized mortality risk and survival can improve advance care planning and discussions about end-of-life care. We developed, validated, and implemented a mortality risk algorithm for older adults with diverse care needs in long-term care (LTC) homes, called the Risk Evaluation for Support: Predictions for Elder-Life in the Community Tool for LTC (RESPECT-LTC). ApproachRESPECT-LTC was developed using routinely-collected health information on residents in LTC homes in Ontario, Canada. Model development used a cohort of LTC residents aged 50 years or older with at least 1 Resident Assessment Instrument—Minimum Data Set (RAI-MDS) record between January 2010 and December 2016. The primary outcome was mortality 6 months after a RAI-MDS assessment. We used proportional hazards regression with robust standard errors to account for clustering by the individual. We validated this algorithm, temporally, in a cohort of LTC residents who were assessed between January and December 2017. We constructed 37 risk bins based on incremental increases in estimated median survival of ~3 weeks among residents at high risk of death and 3 months among residents with lower mortality risk. We implemented and are evaluating the use of RESPECT-LTC for early identification of palliative care needs in LTC homes across Ontario. ResultsDevelopment and validation cohorts included 2,228,176 and 328,204 RAI-MDS assessments, respectively. Mean predicted 6-month mortality risk ranged from 1.38% (95% CI 0.63%-1.61%) in the lowest to 91.97% (95% CI 81.47%-99.9%) in the highest risk group. Estimated median survival spanned from 42 days (15 to 128 d at the 25th and 75th percentiles) in the highest risk group to over 8 years (2,066 to 3,428 d) in the lowest risk group. The algorithm had a c-statistic of 0.730 (95% CI 0.726–0.736) in our validation cohort. ConclusionRESPECT-LTC makes use of routinely-collected information to improve the identification of palliative and end-of-life care needs in LTC. Ongoing evaluation will assess its impact on referrals to palliative care, hospitalization at the end of life, and location of death.
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 | 0.017 | 0.056 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".