Health Care Analytics With Time-Invariant and Time-Variant Feature Importance to Predict Hospital-Acquired Acute Kidney Injury: Observational Longitudinal Study.
Horng Ruey ChuaKaiping ZhengAnantharaman VathsalaKee-Yuan NgiamHui-Kim YapLiangjian LuHo Yee TiongAmartya MukhopadhyayGraeme MacLarenShir-Lynn LimK AkalyaBeng-Chin OoiPublished in: Journal of medical Internet research (2021)
We generated an accurate algorithm from electronic health records through machine learning that predicted AKI by a lead time of at least 48 hours. The prediction threshold could be adjusted during deployment to optimize recall and minimize alert fatigue, while its precision could potentially be augmented by targeted AKI biomarker assessment in the high-risk cohort identified.
Keyphrases
- acute kidney injury
- machine learning
- electronic health record
- big data
- clinical decision support
- healthcare
- adverse drug
- cardiac surgery
- artificial intelligence
- deep learning
- cancer therapy
- sleep quality
- high resolution
- acute care
- cross sectional
- virtual reality
- affordable care act
- neural network
- drug delivery
- mass spectrometry