Development of Multivariable Prediction Models for 30-Day Risk of Readmission After COPD Hospital Admission: A Retrospective Cohort Study Using Electronic Medical Record Data from 7 Hospitals
Bibliographic record
Abstract
BACKGROUND: Approximately 20% of patients who are discharged from hospital for an acute exacerbation of COPD (AECOPD) are readmitted within 30 days. Prediction scores are helpful to identify those who are at higher risk of readmission, such that they can be prioritized for readmission-reducing interventions. OBJECTIVES: To develop and determine the accuracy and precision of a clinical prediction model using data available in electronic medical records to predict 30-day readmission in patients discharged after a hospitalization with an AECOPD. METHODS: A dataset was created using all admissions to General Internal Medicine from 2012 to 2018 at seven hospitals in Toronto, Canada. We fit and internally validated models with six algorithms. RESULTS: Of the 16,314 patients admitted with an exacerbation of COPD, 15.4% were readmitted at 30 days. Top-performing models included LASSO, logistic regression, linear discriminant analysis, and XGBoost with C-statistics of 0.688 ± 0.024, 0.690 ± 0.026, 0.687 ± 0.023, and 0.686 ± 0.022. The four top models had similarly high specificity (96%-98%) with poor sensitivity (14%-20%) at a decision threshold of 50%. At a more aggressive decision threshold of 20%, specificity was less (69%-73%) with a modest improvement in sensitivity (55%-59%). The most important predictor of readmission risk was the number of hospitalizations in the previous year. CONCLUSION: We generated clinical prediction models to predict all-cause 30-day readmissions after an acute exacerbation using data from 7 hospitals' electronic medical records. Further work should be done to improve performance, especially sensitivity.
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 | 0.011 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| 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".