Derivation and external validation of a venous thromboembolism risk prediction model in asparaginase-treated ALL
Bibliographic record
Abstract
ABSTRACT: The incidence of venous thromboembolism (VTE) in patients with acute lymphoblastic leukemia (ALL) receiving asparaginase-based induction is high despite primary thromboprophylaxis. Our aim was to derive and externally validate a VTE risk prediction model in patients with ALL receiving asparaginase-based induction. We conducted a multicenter retrospective cohort study of patients (aged ≥18 years) with newly diagnosed ALL receiving asparaginase-based induction. The derivation and external validation cohorts included 306 and 94 patients, respectively. Primary outcome was VTE at any site. A cause-specific Cox proportional hazards model stratified by thromboprophylaxis and center was performed to identify VTE risk factors in the derivation cohort. A risk prediction model for VTE at 30 days was derived using variables with P value < .05 in the multivariable model and was tested in the validation cohort. VTE risk factors on multivariable analysis in the derivation cohort included D-dimer ≥1 μg fibrinogen equivalent unit per mL (hazard ratio [HR], 2.64; 95% confidence interval [CI], 1.07-6.5) and hemoglobin (HR for each 1 g/dL increment, 1.19; 95% CI, 1.06-1.34) at ALL diagnosis. A VTE risk score based on these variables distinguished between a 4% (95% CI, 0.72-12) and 20% (95% CI, 14-27) 30-day cumulative incidence of VTE in the derivation cohort, with similar findings in the validation cohort (area under the curve, 0.56). The negative predictive value for VTE at 30 days was 96% and 93% in the derivation and validation cohorts, respectively, and the positive predictive value was 20% in both. We derived and validated a model using D-dimer and hemoglobin, which stratifies VTE risk in patients with ALL receiving asparaginase-based induction.
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 | 0.015 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| 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".