A clinical predictive model for post‐hospitalisation venous thromboembolism in patients with inflammatory bowel disease
Bibliographic record
Abstract
BACKGROUND: Patients with inflammatory bowel disease (IBD) are at increased risk of venous thromboembolism (VTE) during hospitalisation and potentially post-discharge. AIMS: To determine the incidence and risk factors for post-discharge VTE in IBD patients and create a point of care predictive model to assess VTE risk. METHODS: Hospitalised IBD patients were identified from our institutional discharge database between 2009 and 2016, and were assessed for VTE by chart review. Risk factors for VTE within 3 months of discharge were determined by univariable and multivariable logistic regression. A point of care model was created using variables from the univariate analysis with P < 0.05, and internally validated by bootstrap methods. RESULTS: Sixty-six of 2161 eligible discharges (3%) were associated with VTE within 6 months of hospitalisation. The median time to event was 37 days (range 3-182 days). On multivariable analysis age >45 years (OR 3.76; 95% CI 1.80-7.89) and multiple admissions (OR 2.62; 95% CI 1.34-5.11) were independently associated with VTE risk. Our final model incorporated age >45 years, multiple admissions, intensive care unit admission, length of admission >7 days and central catheter and was able to discriminate between discharges associated with and without VTE (optimism-corrected c-statistic, 0.70; 95% CI 0.58-0.77). By limiting treatment to a high-risk group, extended thromboprophylaxis could be avoided in 92% of discharges with a miss rate of 1.6% (32/1982 discharges). CONCLUSION: Patients with IBD remain at risk of VTE after hospital discharge. Our model may help clinicians stratify which patients will benefit most from extended thrombophrophylaxis.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".