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

Clinically applicable deep learning for diagnosis and referral in retinal disease

Jeffrey De Fauw, Joseph R. Ledsam, Bernardino Romera‐Paredes, Stanislav Nikolov, Nenad Tomašev, Sam Blackwell, Harry Askham, Xavier Glorot, Brendan O’Donoghue, Daniel Visentin, George van den Driessche, Balaji Lakshminarayanan, Clemens Meyer, Faith Mackinder, S. Miles Bouton, Kareem Ayoub, Reena Chopra, Dominic King, Alan Karthikesalingam, Cían Hughes, Rosalind Raine, J. Randall Hughes, Dawn A. Sim, Catherine Egan, Adnan Tufail, Hugh Montgomery, Demis Hassabis, Geraint Rees, Trevor Back, Peng T. Khaw, Mustafa Suleyman, Julien Cornebise, Pearse A. Keane, Olaf Ronneberger

Nature Medicine · 2018

Read source ↗ All evidence

Summary

This paper describes the development of a clinically applicable deep learning algorithm for automated diagnosis and referral triage in retinal disease, validated in a clinical setting. The work demonstrates how machine learning can support ophthalmological decision-making and patient pathway management. As a medical imaging application published in Nature Medicine, it represents a methodological advance in diagnostic AI rather than a contribution to agricultural or nutritional science.

UK applicability

This paper is not applicable to UK farming systems, soil health, nutrient density or food production. It addresses clinical ophthalmology and diagnostic AI implementation in healthcare settings, which falls outside the scope of Vitagri's Pulse Brain.

Key measures

Diagnostic accuracy, sensitivity, specificity, agreement with clinical referral decisions, as suggested by the title and Nature Medicine publication context (2018)

Outcomes reported

The study reports the development and clinical validation of a deep learning system for automated diagnosis and referral recommendations in retinal diseases. Performance metrics likely include sensitivity, specificity, and diagnostic accuracy compared to clinical ophthalmologists.

Theme
Measurement & metrics
Subject
Other / interdisciplinary
Study type
Research
Study design
Clinical validation study
Source type
Peer-reviewed study
Status
Published
Geography
United Kingdom
System type
Human clinical
DOI
10.1038/s41591-018-0107-6
Catalogue ID
BFmor3g48f-33z51t

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.