Electronic phenotyping of health outcomes of interest using a linked claims-electronic health record database: Findings from a machine learning pilot project.
Teresa B GibsonMichael D NguyenTimothy BurrellFrank YoonJenna WongSai DharmarajanRita Ouellet-HellstromWei HuaYong MaElande BaroSarah BloemersCory PackAdee KennedySengwee TohRobert BallPublished in: Journal of the American Medical Informatics Association : JAMIA (2021)
It is feasible to use machine learning methods to predict an EHR-derived HOI with claims-based predictors. Modeling strategies can be adapted for intended uses, including surveillance, identification of cases for chart review, and outcomes research.
Keyphrases
- electronic health record
- machine learning
- adverse drug
- health insurance
- clinical decision support
- artificial intelligence
- big data
- public health
- quality improvement
- deep learning
- study protocol
- randomized controlled trial
- emergency department
- type diabetes
- bioinformatics analysis
- adipose tissue
- weight loss
- insulin resistance