Key result
ML model using longitudinal BP trajectories predicts 5-year Alzheimer's onset with modest accuracy.
Why the study?
Prior studies linking EHR-derived blood pressure measurements to Alzheimer's disease rely on summary statistics and lack multi-institutional validation.
Does an EHR-based machine learning model using blood pressure trajectories accurately predict Alzheimer's disease onset in older adults with hypertension?
Cohort (n=8,061)
Yes
Does an EHR-based machine learning model using blood pressure trajectories accurately predict Alzheimer's disease onset in older adults with hypertension?
Effect estimate: AUROC 0.66 (95% CI 0.55-0.76)
Using longitudinal blood pressure trajectories from EHR data can provide modest risk stratification for Alzheimer's disease across different institutional cohorts.
INTRODUCTION: Studies investigating the relationship between blood pressure (BP) measurements from electronic health records (EHRs) and Alzheimer's disease (AD) rely on summary statistics, like BP variability, and have only been validated at a single institution. We hypothesize that leveraging BP trajectories can accurately estimate AD risk across different populations. METHODS: In a retrospective cohort study, EHR data from Veterans Affairs (VA) patients were used to train and internally validate a machine learning model to predict AD onset within 5 years. External validation was conducted on patients from Michigan Medicine (MM). RESULTS: The VA and MM cohorts included 6860 and 1201 patients, respectively. Model performance using BP trajectories was modest but comparable (area under the receiver operating characteristic curve [AUROC] = 0.64 [95% confidence interval (CI) = 0.54-0.73] for VA vs. AUROC = 0.66 [95% CI = 0.55-0.76] for MM). CONCLUSION: Approaches that directly leverage BP trajectories from EHR data could aid in AD risk stratification across institutions.
No takes yet. Share an insight, caveat, or question.
Tjandra et al. (2022) conducted a cohort in Alzheimer's disease risk in hypertension (n=8,061). EHR-based longitudinal blood pressure trajectories vs. Blood pressure summary statistics or no blood pressure data was evaluated on Prediction of Alzheimer's disease onset within 5 years (AUROC) (AUROC 0.66, 95% CI 0.55-0.76). An EHR-based machine learning model using longitudinal blood pressure trajectories predicted Alzheimer's disease onset within 5 years with modest accuracy (AUROC 0.66) in an external validation cohort.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: