Antihypertensive use was linked to slightly longer time without recorded cognitive impairment
Source check: Source checked. Not independent scientific confirmation.
Finding: In a retrospective All of Us analysis targeting a high-risk population with model-derived weights, baseline antihypertensive use was associated with slightly longer time without a first recorded mild cognitive impairment diagnosis. The ratio of geometric mean time capped at 48 months was 1.012 overall and 1.026 in a subgroup with cardiometabolic and depressive multimorbidity.
Technology: Regularized logistic regression, cross-fitted XGBoost
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A regularized logistic model fitted to the non-overlapping reference sample estimates target high-risk membership; cross-fitted XGBoost models estimate treatment propensity and outcomes.
- Test and result
- The study trained its risk model in a non-overlapping internal reference set of 83,745 participants and estimated associations in a 37,577-participant analysis set with 500 first recorded MCI diagnoses within 48 months. Model-derived weights target a high-risk population without restricting the cohort to a directly observed high-risk stratum.
- Limitation / still unknown
- The estimates are associations involving baseline medication use and the first recorded diagnosis. Treatment initiation, adherence, causal benefit and external validation were outside the study.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/abs/2610.30709 · https://arxiv.org/html/2610.30709v1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 21 Nov 2026. Review scope: arXiv v1 §4 propensity/outcome models, logistic risk weights, sample construction, Table 3 and Figure 3.
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.