Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records
Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records
Nenad Tomašev,Natalie Harris,28 Authors,S. Mohamed
2021 · DOI: 10.1038/s41596-021-00513-5
Nature Protocols · 90 Citations
TLDR
This protocol can be used by interdisciplinary teams with programming and clinical expertise to build deep-learning prediction models with alternate data sources and prediction tasks to predict various adverse outcomes from structured electronic health records.