S1642 DEVELOPMENT OF A CLINICAL PREDICTION RULE FOR VENOUS THROMBOEMBOLISM IN PATIENTS WITH ACUTE LEUKEMIA
Bibliographic record
Abstract
Background: Risk factors for venous thromboembolism (VTE) in patients with solid tumors are well studied, however studies in patients with acute leukemia (AL) are lacking. Identifying risk factors for VTE in leukemia patients would help to develop tailored VTE prophylaxis or surveillance strategies. Aims: To develop a clinical prediction model for VTE in AL patients. Methods: We conducted a retrospective cohort study of adult patients diagnosed with acute myeloid leukemia and acute lymphoblastic leukemia diagnosed between June 2006 and June 2017 at a tertiary care center in Canada. Outcome of interest was occurrence of imaging-confirmed VTE including proximal upper and lower extremity deep vein thrombosis, pulmonary embolism or thrombosis of unusual sites, including cerebral and splanchnic. Participants were followed until VTE occurrence, death or last follow up. Groups’ characteristics were compared using chi-square, Fisher's exact, or Student's T-tests as appropriate. Potential predictors were evaluated using single variable logistic regression and confirmed with multiple variable logistic regression. The final risk score was derived based on weighed variables and compared using survival analysis. Internal validation was conducted using non-parametric bootstrapping. Results: A total of 501 leukemia patients (427 myeloid and 74 lymphoblastic; 260 males) were included. Venous thromboembolism occurred in 77(15.3%) patients (44 upper extremity DVT, 28 lower extremity DVT or PE, 5 cerebral vein thrombosis. Median time from AL diagnosis to VTE was 64 days (interquartile range 22–130). The cumulative incidence of VTE was 9.6% (n = 48) (95%CI: 7.30–12.47) at 3 months, 12.8% (n = 64) (95%CI: 10.13–15.98) at 6 months, and 14% (n = 71) (95%CI: 11.39–17.50) at 12 months from the AL diagnosis. Of a total of 20 potential predictors, 7 were included in the multi-variable model. The final prediction score that was derived and validated included: previous history of venous thromboembolism (3 points), lymphoblastic leukemia (2 points), and platelet count > 50 x 109/L at the time of diagnosis (1 point). The overall cumulative incidence of venous thromboembolism was 44% in the high risk group (≥ 3 points) versus 10.5% in the low risk group (0–2 points) and it was consistent at 3 (28.8% vs 6.3%), 6 (41.1% vs 7.9%), and 12 (42.5% vs 9.3%) months (Figure; Log-rank p < 0.001).Summary/Conclusion: We derived and internally validated a predictive score of venous thromboembolism risk in acute leukemia patients. FA-A is a fellow of the Canadian Venous Thromboembolism Clinical Trials and Outcomes Research (CanVECTOR) Network; ALL-L is an investigator of the CanVECTOR Network. This study was funded by the CanVECTOR Network which receives grant funding from the Canadian Institutes of Health Research (Funding Reference: CDT-142654).
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".