Validation of a Prediction Model Used at Kaiser Permanente Northwest in Collaboration With Operations
Bibliographic record
Abstract
Background: The LACE risk score is used by Kaiser Permanente Northwest (KPNW) to identify patients at high risk for hospital readmission or mortality. LACE triggers the delivery of Transitions of Care interventions to reduce unnecessary readmissions. However, LACE was put into practice before it was validated for Kaiser Permanente hospitals. This study validated the LACE model in the KPNW patient population using routine electronic medical record data (not research data from the virtual data warehouse) to evaluate the accuracy and applicability of the predictions. The validation was only possible through collaboration with KPNW operations. Methods: This is a retrospective study of adult patients hospitalized from August 2014 to July 2015 at Sunnyside Medical Center (KSMC) at KPNW. Only the initial admission was included. The study outcome was readmission to the hospital or death within 30 days of discharge. The C-statistic was compared to the published value (Van Walraven et al, 2010). We assessed calibration (accuracy) graphically before and after we updated the LACE model with the KSMC-specific intercept. Results: Of the 9,699 patients, 10.8% experienced the outcome. The C-statistic for KPNW (0.728) was slightly higher than the published value from Ontario hospitals (0.7114). The published LACE score was well calibrated with the KPNW population (observed vs predicted risks for the low/mid/high-risk groups were 0.042/0.102/0.256 vs 0.053/0.112/0.234, respectively). The updated LACE model with the KSMC-specific intercept (ie, probability in the lowest-risk patients) resulted in slightly better calibration (predicted risks for the low/mid/high-risk groups were 0.043/0.106/0.247). To target high-risk patients for Transitions of Care interventions, KPNW applies a cut-off of 11 or more LACE points, which resulted in a positive predictive value of 25.6%. Conclusion: The LACE score validated successfully at KPNW’s KSMC, with only a slight underestimate of risk in high-risk patients. Updating LACE improved the predicted risk modestly (1.3%) for high-risk patients. Kaiser Permanente operations will continue to collaborate with colleagues in research to evaluate the LACE+ index and other predictors of readmission and mortality.
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 | 0.023 | 0.046 |
| 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 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".