Early prediction of Alzheimer’s disease and related dementias using real-world electronic health records

Details

• Alternative Title:
  Alzheimers Dement
• Personal Author:
  Li, Qian ; Yang, Xi ; Xu, Jie ; Guo, Yi ; He, Xing ; Hu, Hui ; Lyu, Tianchen ; Marra, David ; Miller, Amber ; Smith, Glenn ; DeKosky, Steven ; Boyce, Richard D. ; Schliep, Karen ; Shenkman, Elizabeth ; Maraganore, Demetrius ; Wu, Yonghui ; Bian, Jiang
• Description:
  Introduction:
  
  This study aims to explore machine learning (ML) methods for early prediction of Alzheimer’s disease (AD) and related dementias (ADRD) using the real-world electronic health records (EHRs).
  
  Methods:
  
  A total of 23,835 ADRD and 1,038,643 control patients were identified from the OneFlorida+ Research Consortium. Two ML methods were used to develop the prediction models. Both knowledge-driven and data-driven approaches were explored. Four computable phenotyping algorithms were tested.
  
  Results:
  
  The gradient boosting tree (GBT) models trained with the data-driven approach achieved the best area under the curve (AUC) scores of 0.939, 0.906, 0.884, and 0.854 for early prediction of ADRD 0, 1, 3, or 5 years before diagnosis, respectively. A number of important clinical and sociodemographic factors were identified.
  
  Discussion:
  
  We tested various settings and showed the predictive ability of using ML approaches for early prediction of ADRD with EHRs. The models can help identify high-risk individuals for early informed preventive or prognostic clinical decisions.
  
  
• Subjects:
  Algorithms Alzheimer Disease Electronic Health Records Humans Machine Learning Prognosis
• Keywords:
  Alzheimer’s Disease (AD) Alzheimer’s Disease And Related Dementias (ADRD) Data-driven Approach Machine Learning Real-world Data Risk Prediction
• Source:
  Alzheimers Dement. 19(8):3506-3518
• Pubmed ID:
  36815661
• Pubmed Central ID:
  PMC10976442
• Document Type:
  Journal Article
• Funding:
  R01AG076234/AG/NIA NIH HHSUnited States/ ; R56 AG069880/AG/NIA NIH HHSUnited States/ ; U18 DP006512/DP/NCCDPHP CDC HHSUnited States/ ; R01CA246418 R01/CA/NCI NIH HHSUnited States/ ; K01 AG058781/AG/NIA NIH HHSUnited States/ ; R21AG068717/AG/NIA NIH HHSUnited States/ ; R56AG069880/AG/NIA NIH HHSUnited States/ ; U18DP006512/ACL/ACL HHSUnited States/ ; R21 AG068717/AG/NIA NIH HHSUnited States/ ; R01 AG076234/AG/NIA NIH HHSUnited States/ ; R01 CA246418/CA/NCI NIH HHSUnited States/
• Volume:
  19
• Issue:
  8
• Collection(s):
  CDC Public Access
• Main Document Checksum:
  urn:sha256:d91a815f06e3483ed6ca934727c49dce2bebff7ca3a35b1d3296b8a78565d9a7
• Download URL:
  https://stacks.cdc.gov/view/cdc/153596/cdc_153596_DS1.pdf
• File Type:
  [PDF - 1.25 MB ]