A clinically applicable approach to continuous prediction of future acute kidney injury

Nenad Tomašev (), Xavier Glorot, Jack W. Rae, Michal Zielinski, Harry Askham, Andre Saraiva, Anne Mottram, Clemens Meyer, Suman Ravuri, Ivan Protsyuk, Alistair Connell, Cían O. Hughes, Alan Karthikesalingam, Julien Cornebise, Hugh Montgomery, Geraint Rees, Chris Laing, Clifton R. Baker, Kelly Peterson, Ruth Reeves, Demis Hassabis, Dominic King, Mustafa Suleyman, Trevor Back, Christopher Nielson, Joseph R. Ledsam () and Shakir Mohamed
Additional contact information
Nenad Tomašev: DeepMind
Xavier Glorot: DeepMind
Jack W. Rae: DeepMind
Michal Zielinski: DeepMind
Harry Askham: DeepMind
Andre Saraiva: DeepMind
Anne Mottram: DeepMind
Clemens Meyer: DeepMind
Suman Ravuri: DeepMind
Ivan Protsyuk: DeepMind
Alistair Connell: DeepMind
Cían O. Hughes: DeepMind
Alan Karthikesalingam: DeepMind
Julien Cornebise: DeepMind
Hugh Montgomery: University College London
Geraint Rees: University College London
Chris Laing: University College London Hospitals
Clifton R. Baker: Department of Veterans Affairs
Kelly Peterson: VA Salt Lake City Healthcare System
Ruth Reeves: Department of Veterans Affairs
Demis Hassabis: DeepMind
Dominic King: DeepMind
Mustafa Suleyman: DeepMind
Trevor Back: DeepMind
Christopher Nielson: University of Nevada School of Medicine
Joseph R. Ledsam: DeepMind
Shakir Mohamed: DeepMind

Nature, 2019, vol. 572, issue 7767, 116-119

Abstract: Abstract The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients1. To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records2–17 and using acute kidney injury—a common and potentially life-threatening condition18—as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests9. Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment.

Date: 2019
References: Add references at CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://www.nature.com/articles/s41586-019-1390-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:572:y:2019:i:7767:d:10.1038_s41586-019-1390-1

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-019-1390-1

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().