A simplification of the Kaiser Permanente inpatient risk adjustment methodology accurately predicted in-hospital mortality: A retrospective cohort study
Bibliographic record
Abstract
Abstract Objective We simplified and evaluated the Kaiser Permanente inpatient risk adjustment methodology (KP method) to predict in-hospital mortality, using open-source tools to measure comorbidity and diagnosis groups, and removing troponin, which is difficult to standardize across clinical assays. Study Design and Setting Retrospective cohort study of adult general medical inpatients at 7 hospitals in Ontario, Canada. Results In 206,155 unique hospitalizations with 6.9% in-hospital mortality, the simplified KP method accurately predicted the risk of mortality. Bias-corrected c-statistics were 0.874 (95%CI 0.872-0.877) with troponin and 0.873 (95%CI 0.871-0.876) without troponin, and calibration was excellent for both approaches. Discrimination and calibration were similar with and without troponin for patients with heart failure and acute myocardial infarction. The Laboratory-based Acute Physiology Score (LAPS, a component of the KP method) predicted inpatient mortality on its own with and without troponin with bias-corrected c-statistics of 0.687 (95%CI 0.682-0.692) and 0.680 (95%CI 0.675-0.685), respectively. LAPS was well calibrated, except at very high scores. Conclusion A simplification of the KP method accurately predicted in-hospital mortality risk in an external general medicine cohort. Without troponin, and using common open-source tools, the KP method can be implemented for risk adjustment in a wider range of settings.
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 | 0.010 | 0.026 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".