Improvement in the Prediction of Cerebrovascular Events With White Matter Hyperintensity
Bibliographic record
Abstract
Background It remains unclear if white matter hyperintensity (WMH) on magnetic resonance imaging adds relevant cerebrovascular prognostic information beyond vascular risk factors and demographics alone. Methods and Results We performed a post hoc analysis of hypertensive individuals in SPRINT‐MIND (Systolic Blood Pressure Intervention Trial–Memory and Cognition in Decreased Hypertension). The primary outcome was incident stroke or cognitive impairment (mild cognitive impairment or dementia). We fit logistic regression models with the predictors of Atherosclerotic Cardiovascular Disease Risk Score, age, sex, race, education, current cigarette smoking, and the SPRINT‐MIND randomization arm. WMH was subsequently included in the model to determine if it improved area under the receiver operating curve using the DeLong test. We used a structural equation model to determine the indirect effect on the primary outcome mediated through WMH. We included 727 individuals (mean age at baseline 67.7±8.4 years, 61.1% were men, 62.6% were non‐Hispanic White, and mean years of follow‐up was 3.6±0.9). Of the 727 individuals, 67 (9.2%) developed incident stroke or cognitive decline. The area under the receiver operating curve of the baseline model (without WMH) was 0.75 (95% CI, 0.70–0.81), and after the addition of WMH it increased to 0.81 (95% CI, 0.76–0.86) ( P =0.004 for difference). The mediation analysis showed that 26.3% of the vascular risk's effect on the primary outcome is indirectly mediated through WMH. Conclusions In adult hypertensive individuals, we found that the addition of WMH to models predicting incident stroke or cognitive impairment improved the prognostic ability above vascular risk and demographics alone to a level consistent with excellent prediction. Registration Information REGISTRATION: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT01206062.
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 | 0.008 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| 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".