Pulse Brain · Growing Health Evidence Index
Tier 3 — Observational / field trialPeer-reviewed

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

Nenad Tomašev, Xavier Glorot, Jack W. Rae, Michał Zieliński, Harry Askham, André Saraiva, Anne Mottram, Clemens Meyer, Suman Ravuri, Ivan Protsyuk, Alistair Connell, Cían 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, Shakir Mohamed

Nature · 2019

Read source ↗ All evidence

Summary

This Nature publication describes a machine learning approach to continuously predict future acute kidney injury in clinical patients, as suggested by the title and prominent authorship from DeepMind and healthcare institutions. The work appears to bridge computational prediction and clinical implementation. Without access to the abstract, the precise validation cohorts, performance benchmarks, and clinical deployment setting remain uncertain; however, the emphasis on 'clinically applicable' suggests translation to real-world hospital workflows.

UK applicability

If validated on UK NHS hospital data or implemented within UK clinical practice, findings would be directly applicable to acute kidney injury prevention and patient risk stratification in the NHS. Generalisation to other health systems would depend on model validation across diverse clinical populations and electronic health record systems.

Key measures

Model performance metrics for AKI prediction (likely sensitivity, specificity, area under receiver operating characteristic curve); clinical applicability and timing of predictions

Outcomes reported

The study reports development and validation of a machine learning model for continuous prediction of acute kidney injury (AKI) risk in hospitalised patients. As suggested by the title, the approach aims to provide clinically applicable, real-time risk stratification.

Theme
Measurement & metrics
Subject
Measurement methods & nutrient profiling
Study type
Research
Study design
Research
Source type
Peer-reviewed study
Status
Published
Geography
United Kingdom
System type
Human clinical
DOI
10.1038/s41586-019-1390-1
Catalogue ID
BFmommpb3d-czmoz2

Topic tags

Pulse AI · ask about this record

Dig deeper with Pulse AI.

Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.