Abstract TMP105: Development and Validation of a Risk Prediction Model for Ischemic Stroke Among Individuals Newly Diagnosed With Cancer
Bibliographic record
Abstract
Introduction: Cancer is an emerging risk factor for ischemic stroke. The risk of stroke is highest during the first year after a new diagnosis of cancer, but no tools exist to identify which patients are at the highest risk.. Methods: Using linked clinical and administrative health databases, we conducted a population-based retrospective cohort study of adults in Ontario, Canada with newly diagnosed cancer from 2010 - 2021 (excluding non-melanoma skin cancer & central nervous system malignancies). Patients were randomly selected for model derivation (60%) or validation (40%). The final model predicting stroke within 1 year following cancer diagnosis was derived using multivariable Fine-Gray regression with candidate predictors selected via backward elimination. Sub-distribution adjusted hazard ratios (aHR) and 95% confidence intervals (CI) were calculated, where all-cause mortality was treated as a competing event. Model performance of the validation cohort was assessed using the C-statistic & calibration plots for discrimination and calibration, respectively. Results: Of the 698,566 eligible patients, 418,911 were randomly allocated to derivation, and 279,576 to validation. The overall rate of stroke per 1000 person-years was 6.7 (6.4 - 6.9) for the derivation cohort. The final model included 22 predictors: age, sex, long-term care residency, history of heart failure, hypertension, dementia, asthma, atrial fibrillation, dyslipidemia, liver disease, ischemic stroke, transient ischemic attack, valvular disease, venous thromboembolism, hospitalization within the last 3 months, cancer type, cancer stage, cancer surgery or chemotherapy 3 months following diagnosis, and several 2-way interactions with age & cancer type. Discrimination was good, with a c-statistic of 0.73 in the validation cohort. The model was well calibrated, with points following the 45-degree line (Fig 1). Conclusion: We derived and validated a risk prediction model for ischemic stroke in patients with a new cancer diagnosis with good discrimination. Although our results require external validation, it has potential to identify individuals at highest risk for future randomized trials.
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 | 0.005 | 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 | 0.001 | 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) | 0.002 | 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".