Development and Internal Validation of a Prediction Model for Early Hospital Readmissions in Kidney Transplant Recipients
Bibliographic record
Abstract
Background Early hospital readmission or EHR (i.e., an unplanned rehospitalization event within 30-days of initial discharge) following kidney transplantation is associated with poor clinical outcomes and confers high healthcare costs. Development of an EHR risk prediction model will enable identification of higher risk patients and the opportunity to reduce EHR and improve clinical outcomes. However, there are few EHR risk prediction models for kidney transplant recipients (KTR), and none developed or validated in a Canadian centre. Methods We conducted a single-centre, retrospective cohort study, including adult patients who received a kidney transplant between July 1, 2004 and December 31, 2014 and were followed for at least 30 days after discharge from the transplant admission. EHR risk prediction models were developed using stepwise backward logistic regression and compared for predictive efficacy using ROC curves. Bootstrapping was used to internally validate the final EHR risk prediction moDedel. Results In our cohort of 1381 KTR, the majority were male (60%), white (64%), and on hemodialysis pre-transplant (65%). There were 267 patients who experienced at least one EHR post-transplant. Our full model contained 14 variables with a moderate discrimination (ROC=0.65). The most parsimonious model resulted in a similar discrimination, (ROC=0.64), and consisted of 12 variables, with no individual variable being highly predictive of EHR (Table 1). Internal validation of our parsimonious model resulted in slightly lower discrimination vs. the development model (ROC=0.61). Conclusions Our prediction model was only modestly predictive of EHR in Canadian cohort of kidney transplant recipients. To improve model performance, additional predictors such as surgical complications and infections may need to be considered.
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 | 0.021 | 0.031 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| 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".