1. Developing Deep Learning Continuous Risk Models for Early Adverse Event Prediction in Electronic Health Records: an AKI Case Study
- Author
-
Ivan Protsyuk, Xavier Glorot, Christopher Nielson, Alistair Connell, Cian Hughes, Shakir Mohamed, Chris Laing, Julien Cornebise, Andre Saraiva, Ruth M. Reeves, Demis Hassabis, Alan Karthikesalingam, Hugh Montgomery, Jack W. Rae, Clemens Meyer, Dominic King, Mustafa Suleyman, Suman V. Ravuri, Michal Zielinski, Anne Mottram, Harry Askham, Geraint Rees, Joseph R. Ledsam, Clifton R. Baker, Nenad Tomasev, Kelly S. Peterson, and Trevor Back
- Subjects
business.industry ,Deep learning ,Medicine ,Artificial intelligence ,Medical emergency ,Health records ,business ,Adverse effect ,medicine.disease - Abstract
Early detection of patient deterioration is key to unlocking the potential for targeted preventative care and improving patient outcomes. This protocol describes a workflow for developing deep learning continuous risk models for early prediction of future acute adverse events from electronic health records (EHR), taking the prediction of the risk of future acute kidney injury (AKI) as an exemplar. The protocol consists of 34 steps grouped into the following stages: formal problem definition, data processing, model architecture selection, risk calibration and uncertainty, and evaluating model generalisability. For the protocol to be applicable to modelling the future risk of a particular condition, the problem formulation should be clinically and physiologically plausible and there needs to be sufficient associated predictive signal in routinely collected EHR data. Prospective validation is key in evaluating whether retrospective models developed by following the proposed protocol are clinically applicable and useful.
- Published
- 2019
- Full Text
- View/download PDF