Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.

<h4>Purpose</h4>Leveraging an artificial intelligence system (AI) for glaucoma screening can mitigate the current challenges and provide prompt detection and management crucial in averting irreversible blindness. The study reports the real-world performance of a glaucoma AI system deploy...

Full description

Saved in:
Bibliographic Details
Main Authors: Sirisha Senthil, Divya Parthasarathy Rao, Florian M Savoy, Kalpa Negiloni, Shreya Bhandary, Raghava Chary, Garudadri Chandrashekar
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0324883
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849707170293088256
author Sirisha Senthil
Divya Parthasarathy Rao
Florian M Savoy
Kalpa Negiloni
Shreya Bhandary
Raghava Chary
Garudadri Chandrashekar
author_facet Sirisha Senthil
Divya Parthasarathy Rao
Florian M Savoy
Kalpa Negiloni
Shreya Bhandary
Raghava Chary
Garudadri Chandrashekar
author_sort Sirisha Senthil
collection DOAJ
description <h4>Purpose</h4>Leveraging an artificial intelligence system (AI) for glaucoma screening can mitigate the current challenges and provide prompt detection and management crucial in averting irreversible blindness. The study reports the real-world performance of a glaucoma AI system deployed on a smartphone-based fundus camera across various severities of glaucoma.<h4>Methods</h4>In this prospective comparative study at a tertiary care glaucoma clinic, consecutive patients were evaluated by a glaucoma specialist using clinical assessment, visual field tests, and SD-OCT, and categorized as definite glaucoma, glaucoma suspect, or no glaucoma. For glaucoma patients, severity was determined using Hoddap-Parrish-Anderson criteria based on visual field mean deviation (MD). A disc-centered image per eye was captured using a validated portable non-mydriatic fundus camera. The AI tool's ability to detect referral-warranted glaucoma (glaucoma and glaucoma suspects) versus no glaucoma was compared to the specialist's diagnosis.<h4>Results</h4>We included 213 participants with a mean age of 55 ± 14.7 years (18, 88). The glaucoma specialist diagnosed 129 subjects as definite glaucoma (early-23, moderate-31, severe-75), 33-disc suspects and 51 as no-glaucoma. The automated AI system based on fundus images achieved an overall diagnostic accuracy of 92.02%, sensitivity of 91.36% (95%CI 85.93% to 95.19%) and specificity of 94.12% (83.76% to 98.77%) for referral warranted glaucoma. The 14 false negatives included 5-disc suspects and 9 definite glaucoma (3-early, 3-moderate and 3-advanced glaucoma). The sensitivity of AI for detecting early, moderate and advanced glaucoma was 86.9% (95%CI 66.4-97.2), 90.3% (95%CI 74.3-97.96), and 96% (88.75% to 99.17%) respectively.<h4>Conclusion</h4>In a real-world setting, the AI-based offline tool integrated on a smartphone fundus camera showed a promising performance in detecting referral-warranted glaucoma compared to a glaucoma specialist's diagnosis. The AI showed higher accuracy in detecting advanced glaucoma followed by moderate and early glaucoma.
format Article
id doaj-art-2bf99264d1054ead9bd0efeff9ead138
institution DOAJ
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-2bf99264d1054ead9bd0efeff9ead1382025-08-20T03:16:00ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01206e032488310.1371/journal.pone.0324883Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.Sirisha SenthilDivya Parthasarathy RaoFlorian M SavoyKalpa NegiloniShreya BhandaryRaghava CharyGarudadri Chandrashekar<h4>Purpose</h4>Leveraging an artificial intelligence system (AI) for glaucoma screening can mitigate the current challenges and provide prompt detection and management crucial in averting irreversible blindness. The study reports the real-world performance of a glaucoma AI system deployed on a smartphone-based fundus camera across various severities of glaucoma.<h4>Methods</h4>In this prospective comparative study at a tertiary care glaucoma clinic, consecutive patients were evaluated by a glaucoma specialist using clinical assessment, visual field tests, and SD-OCT, and categorized as definite glaucoma, glaucoma suspect, or no glaucoma. For glaucoma patients, severity was determined using Hoddap-Parrish-Anderson criteria based on visual field mean deviation (MD). A disc-centered image per eye was captured using a validated portable non-mydriatic fundus camera. The AI tool's ability to detect referral-warranted glaucoma (glaucoma and glaucoma suspects) versus no glaucoma was compared to the specialist's diagnosis.<h4>Results</h4>We included 213 participants with a mean age of 55 ± 14.7 years (18, 88). The glaucoma specialist diagnosed 129 subjects as definite glaucoma (early-23, moderate-31, severe-75), 33-disc suspects and 51 as no-glaucoma. The automated AI system based on fundus images achieved an overall diagnostic accuracy of 92.02%, sensitivity of 91.36% (95%CI 85.93% to 95.19%) and specificity of 94.12% (83.76% to 98.77%) for referral warranted glaucoma. The 14 false negatives included 5-disc suspects and 9 definite glaucoma (3-early, 3-moderate and 3-advanced glaucoma). The sensitivity of AI for detecting early, moderate and advanced glaucoma was 86.9% (95%CI 66.4-97.2), 90.3% (95%CI 74.3-97.96), and 96% (88.75% to 99.17%) respectively.<h4>Conclusion</h4>In a real-world setting, the AI-based offline tool integrated on a smartphone fundus camera showed a promising performance in detecting referral-warranted glaucoma compared to a glaucoma specialist's diagnosis. The AI showed higher accuracy in detecting advanced glaucoma followed by moderate and early glaucoma.https://doi.org/10.1371/journal.pone.0324883
spellingShingle Sirisha Senthil
Divya Parthasarathy Rao
Florian M Savoy
Kalpa Negiloni
Shreya Bhandary
Raghava Chary
Garudadri Chandrashekar
Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.
PLoS ONE
title Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.
title_full Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.
title_fullStr Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.
title_full_unstemmed Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.
title_short Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages.
title_sort evaluating real world performance of an automated offline glaucoma ai on a smartphone fundus camera across glaucoma severity stages
url https://doi.org/10.1371/journal.pone.0324883
work_keys_str_mv AT sirishasenthil evaluatingrealworldperformanceofanautomatedofflineglaucomaaionasmartphonefunduscameraacrossglaucomaseveritystages
AT divyaparthasarathyrao evaluatingrealworldperformanceofanautomatedofflineglaucomaaionasmartphonefunduscameraacrossglaucomaseveritystages
AT florianmsavoy evaluatingrealworldperformanceofanautomatedofflineglaucomaaionasmartphonefunduscameraacrossglaucomaseveritystages
AT kalpanegiloni evaluatingrealworldperformanceofanautomatedofflineglaucomaaionasmartphonefunduscameraacrossglaucomaseveritystages
AT shreyabhandary evaluatingrealworldperformanceofanautomatedofflineglaucomaaionasmartphonefunduscameraacrossglaucomaseveritystages
AT raghavachary evaluatingrealworldperformanceofanautomatedofflineglaucomaaionasmartphonefunduscameraacrossglaucomaseveritystages
AT garudadrichandrashekar evaluatingrealworldperformanceofanautomatedofflineglaucomaaionasmartphonefunduscameraacrossglaucomaseveritystages