Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records

Nenad Tomašev
Sebastien Baur
Anne Mottram
Xavier Glorot
Jack William Rae
Michal Zielinski
Harry Askham
Andre Saraiva
Valerio Magliulo
Clemens Meyer
Suman Venkatesh Ravuri
Alistair Connell
Cían Hughes
Julien Cornebise
Hugh Montgomery
Geraint Rees
Christopher Laing
Clifton R. Baker
Thomas Osborne
Ruth Reeves
Demis Hassabis
Dominic King
Mustafa Suleyman
Trevor John Back
Christopher Nielsen
Martin Gamunu Seneviratne
Shakir Mohamad
Nature Protocols (2021)
Google Scholar

Abstract

Early prediction of patient outcomes is important for targeting preventive care. This protocol describes a practical workflow for developing deep-learning risk models that can predict various clinical and operational outcomes from structured electronic health record (EHR) data. The protocol comprises five main stages: formal problem definition, data pre-processing, architecture selection, calibration and uncertainty, and generalizability evaluation. We have applied the workflow to four endpoints (acute kidney injury, mortality, length of stay and 30-day hospital readmission). The workflow can enable continuous (e.g., triggered every 6 h) and static (e.g., triggered at 24 h after admission) predictions. We also provide an open-source codebase that illustrates some key principles in EHR modeling. 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.