Discharge Prediction for Patients Undergoing Inpatient Surgery: Development and validation of the DEPENDENSE score
Bibliographic record
Abstract
BACKGROUND: A substantial proportion of patients undergoing inpatient surgery each year is at risk for postoperative institutionalization and loss of independence. Reliable individualized preoperative prediction of adverse discharge can facilitate advanced care planning and shared decision making. METHODS: Using hospital registry data from previously home-dwelling adults undergoing inpatient surgery, we retrospectively developed and externally validated a score predicting adverse discharge. Multivariable logistic regression analysis and bootstrapping were used to develop the score. Adverse discharge was defined as in-hospital mortality or discharge to a skilled nursing facility. The model was subsequently externally validated in a cohort of patients from an independent hospital. RESULTS: In total, 106 164 patients in the development cohort and 92 962 patients in the validation cohort were included, of which 16 624 (15.7%) and 7717 (8.3%) patients experienced adverse discharge, respectively. The model was predictive of adverse discharge with an area under the receiver operating characteristic curve (AUC) of 0.87 (95% CI 0.87-0.88) in the development cohort and an AUC of 0.86 (95% CI 0.86-0.87) in the validation cohort. CONCLUSION: Using preoperatively available data, we developed and validated a prediction instrument for adverse discharge following inpatient surgery. Reliable prediction of this patient centered outcome can facilitate individualized operative planning to maximize value of care.
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 | 0.007 | 0.030 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| 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".