African American patients have a higher probability of cognitive impairment after incident stroke: An analysis of national electronic health record data.

BACKGROUND: Cognitive impairment (CI) and stroke are diseases with significant disparities in race and geography. Post stroke cognitive impairment (PSCI) can be as high as 15-70 % but few studies have utilized large administrative or electronic health records (EHR) to evaluate trends in PSCI. We utilized an EHR database to evaluate for disparities in PSCI in a large sample of patients after first recorded stroke to evaluate for disparities in race. METHODS: This is a retrospective cohort analysis of Cerner Health Facts® EHR database, which is comprised of EHR data from hundreds of hospitals/clinics in the US from 2009-2018. We evaluated patients ≥40 years of age with a first time ischemic stroke (IS) diagnosis for PSCI using ICD9/10 codes for both conditions. Patients with first stroke in the Cerner database and no pre-existing cognitive impairment were included, we compared hazard ratios for developing PSCI for patient characteristics RESULTS: A total of 150,142 IS patients with follow-up data and no pre-existing evidence of CI were evaluated. Traditional risk factors of age, female sex, kidney injury, hypertension, and hyperlipidemia were associated with PSCI. Only African American stroke survivors had a higher probability of developing PSCI compared to White survivors (HR 1.347, 95 % CI (1.270, 1.428)) and this difference was most prominent in the South. Among those to develop PSCI, median time to documentation was 1.8 years in African American survivors. CONCLUSION: In a large national database, African American stroke survivors had a higher probability of PSCI five years after stroke than White survivors.

Deep learning to predict rapid progression of Alzheimer's disease from pooled clinical trials: A retrospective study.

The rate of progression of Alzheimer's disease (AD) differs dramatically between patients. Identifying the most is critical because when their numbers differ between treated and control groups, it distorts the outcome, making it impossible to tell whether the treatment was beneficial. Much recent effort, then, has gone into identifying RPs. We pooled de-identified placebo-arm data of three randomized controlled trials (RCTs), EXPEDITION, EXPEDITION 2, and EXPEDITION 3, provided by Eli Lilly and Company. After processing, the data included 1603 mild-to-moderate AD patients with 80 weeks of longitudinal observations on neurocognitive health, brain volumes, and amyloid-beta (Aß) levels. RPs were defined by changes in four neurocognitive/functional health measures. We built deep learning models using recurrent neural networks with attention mechanisms to predict RPs by week 80 based on varying observation periods from baseline (e.g., 12, 28 weeks). Feature importance scores for RP prediction were computed and temporal feature trajectories were compared between RPs and non-RPs. Our evaluation and analysis focused on models trained with 28 weeks of observation. The models achieved robust internal validation area under the receiver operating characteristic (AUROCs) ranging from 0.80 (95% CI 0.79-0.82) to 0.82 (0.81-0.83), and the area under the precision-recall curve (AUPRCs) from 0.34 (0.32-0.36) to 0.46 (0.44-0.49). External validation AUROCs ranged from 0.75 (0.70-0.81) to 0.83 (0.82-0.84) and AUPRCs from 0.27 (0.25-0.29) to 0.45 (0.43-0.48). Aß plasma levels, regional brain volumetry, and neurocognitive health emerged as important factors for the model prediction. In addition, the trajectories were stratified between predicted RPs and non-RPs based on factors such as ventricular volumes and neurocognitive domains. Our findings will greatly aid clinical trialists in designing tests for new medications, representing a key step toward identifying effective new AD therapies.