P4‐554: An Ehr‐based Cohort Discovery Tool for Identifying Probable Ad

Tjandra, Donna; Migrino, Raymond Q.; Giordani, Bruno; Wiens, Jenna

doi:10.1016/j.jalz.2019.08.101

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Electronic health records (EHRs), which capture a wide variety of important health events and include patients with the most severe manifestations of AD or disability, might be useful resources to identify new targets for intervention and help improve AD care. 8,[12][13][14] In this retrospective study, our goal was to identify distinct subphenotypes from routinely collected structured EHR data. Instead of targeting the precise biomarker-confirmed AD phenotype, we aimed to identify subgroups of patients given a clinical diagnosis of AD by their treating physician (which we categorize as "probable AD and related dementia") using broader and more readily available EHR data to characterize their clinical features.…”

Section: Introductionmentioning

confidence: 99%

“…Prospective studies, in general, are resource‐ and time‐intensive 10,11 and retrospective studies using existing data might offer complementary insights, improving our understanding for better diagnosis and treatment of AD. Electronic health records (EHRs), which capture a wide variety of important health events and include patients with the most severe manifestations of AD or disability, might be useful resources to identify new targets for intervention and help improve AD care 8,12‐14 …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data‐driven discovery of probable Alzheimer's disease and related dementia subphenotypes using electronic health records

Wang

et al. 2020

Learning Health Systems

View full text Add to dashboard Cite

Introduction: We sought to assess longitudinal electronic health records (EHRs) using machine learning (ML) methods to computationally derive probable Alzheimer's Disease (AD) and related dementia subphenotypes. Methods: A retrospective analysis of EHR data from a cohort of 7587 patients seen at a large, multi-specialty urban academic medical center in New York was conducted. Subphenotypes were derived using hierarchical clustering from 792 probable AD patients (cases) who had received at least one diagnosis of AD using their clinical data. The other 6795 patients, labeled as controls, were matched on age and gender with the cases and randomly selected in the ratio of 9:1. Prediction models with multiple ML algorithms were trained on this cohort using 5-fold cross-validation. XGBoost was used to rank the variable importance. Results: Four subphenotypes were computationally derived. Subphenotype A (n = 273; 28.2%) had more patients with cardiovascular diseases; subphenotype B (n = 221; 27.9%) had more patients with mental health illnesses, such as depression and anxiety; patients in subphenotype C (n = 183; 23.1%) were overall older (mean (SD) age, 79.5 (5.4) years) and had the most comorbidities including diabetes, cardiovascular diseases, and mental health disorders; and subphenotype D (n = 115; 14.5%) included patients who took antidementia drugs and had sensory problems, such as deafness and hearing impairment. The 0-year prediction model for AD risk achieved an area under the receiver operating curve (AUC) of 0.764

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%