Global Search

Search articles, concepts, and chapters

Am J OphthalmolNovember 202316 citations

Application of a Deep Learning System to Detect Papilledema on Nonmydriatic Ocular Fundus Photographs in an Emergency Department.

Biousse Valérie, Najjar Raymond P, Tang Zhiqun, Lin Mung Yan, Wright David W, Keadey Matthew T, Wong Tien Y, Bruce Beau B, Milea Dan, Newman Nancy J


AI Summary

A deep learning system accurately detected papilledema on ED fundus photos, showing strong potential as a diagnostic aid for non-ophthalmologists to improve critical early detection.

Abstract

Purpose

The Fundus photography vs Ophthalmoscopy Trial Outcomes in the Emergency Department (FOTO-ED) studies showed that ED providers poorly recognized funduscopic findings in patients in the ED. We tested a modified version of the Brain and Optic Nerve Study Artificial Intelligence (BONSAI) deep learning system on nonmydriatic fundus photographs from the FOTO-ED studies to determine if the deep learning system could have improved the detection of papilledema had it been available to ED providers as a real-time diagnostic aid.

Design

Retrospective secondary analysis of a cohort of patients included in the FOTO-ED studies.

Methods

The testing data set included 1608 photographs obtained from 828 patients in the FOTO-ED studies. Photographs were reclassified according to the optic disc classification system used by the deep learning system ("normal optic discs," "papilledema," and "other optic disc abnormalities"). The system's performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 1-vs-rest strategy, with reference to expert neuro-ophthalmologists.

Results

The BONSAI deep learning system successfully distinguished normal from abnormal optic discs (AUC 0.92 [95% confidence interval {CI} 0.90-0.93]; sensitivity 75.6% [73.7%-77.5%] and specificity 89.6% [86.3%-92.8%]), and papilledema from normal and others (AUC 0.97 [0.95-0.99]; sensitivity 84.0% [75.0%-92.6%] and specificity 98.9% [98.5%-99.4%]). Six patients with missed papilledema in 1 eye were correctly identified by the deep learning system as having papilledema in the other eye.

Conclusions

The BONSAI deep learning system was able to reliably identify papilledema and normal optic discs on nonmydriatic photographs obtained in the FOTO-ED studies. Our deep learning system has excellent potential as a diagnostic aid in EDs and non-ophthalmology clinics equipped with nonmydriatic fundus cameras. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.


MeSH Terms

HumansFundus OculiPapilledemaRetrospective StudiesDeep LearningArtificial IntelligenceEmergency Service, HospitalEye DiseasesPhotography

Key Concepts4

The BONSAI deep learning system successfully distinguished normal from abnormal optic discs on nonmydriatic fundus photographs with an AUC of 0.92 (95% CI 0.90-0.93), sensitivity of 75.6% (73.7%-77.5%), and specificity of 89.6% (86.3%-92.8%).

DiagnosisCohortRetrospective secondary analysisn=1608 photographs from 828 patientsCh5Ch7

The BONSAI deep learning system distinguished papilledema from normal and other optic disc abnormalities on nonmydriatic fundus photographs with an AUC of 0.97 (95% CI 0.95-0.99), sensitivity of 84.0% (75.0%-92.6%), and specificity of 98.9% (98.5%-99.4%).

DiagnosisCohortRetrospective secondary analysisn=1608 photographs from 828 patientsCh5Ch7

The BONSAI deep learning system correctly identified papilledema in the other eye for six patients who had missed papilledema in one eye, demonstrating its potential as a diagnostic aid.

DiagnosisCohortRetrospective secondary analysisn=6 patientsCh5Ch7

The BONSAI deep learning system reliably identified papilledema and normal optic discs on nonmydriatic photographs obtained in the FOTO-ED studies, suggesting its potential as a diagnostic aid in Emergency Departments and non-ophthalmology clinics equipped with nonmydriatic fundus cameras.

DiagnosisCohortRetrospective secondary analysisn=1608 photographs obtained from 828 pa…Ch5Ch7

Is this article assigned to the wrong chapter(s)? Let us know.