Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergencies

Introduction: ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage) is a GPT-4-based triage tool designed to assess ophthalmic emergencies using a three-tier color-coded system. This study compares ASSORT to the Rescue triage method, using the ophthalmologist’s final assessment...

Full description

Saved in:
Bibliographic Details
Main Authors: Claudio Xompero, Lorenzo Rossi, Francesca Amoroso, Antonio Bechara Ghobril, Diana Elena Ionita, Eric H. Souied, Carl-Joe Mehanna
Format: Article
Language:English
Published: Elsevier 2025-10-01
Series:AJO International
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2950253525000620
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246162875318272
author Claudio Xompero
Lorenzo Rossi
Francesca Amoroso
Antonio Bechara Ghobril
Diana Elena Ionita
Eric H. Souied
Carl-Joe Mehanna
author_facet Claudio Xompero
Lorenzo Rossi
Francesca Amoroso
Antonio Bechara Ghobril
Diana Elena Ionita
Eric H. Souied
Carl-Joe Mehanna
author_sort Claudio Xompero
collection DOAJ
description Introduction: ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage) is a GPT-4-based triage tool designed to assess ophthalmic emergencies using a three-tier color-coded system. This study compares ASSORT to the Rescue triage method, using the ophthalmologist’s final assessment as the reference standard. Materials and methods: A prospective study was conducted at the Créteil University Hospital from April to June 2024. Each patient underwent triage using ASSORT, followed by the Rescue triage method. Both tools used the same color-coding system to stratify severity: yellow for emergency cases, green for urgent cases, and white for non-urgent cases. An examining ophthalmologist in their final year of residency performed the final assessment. Concordance between the ophthalmologist and each of the tools was analyzed using Cohen’s kappa coefficient, alongside precision and recall metrics. Results: Fifty-one patients were included. Case severities were distributed as follows: 22/51 white, 27/51 green, and 2/51 yellow, with conjunctivitis (17.5 %) and corneal abrasions (12.5 %) being the two most common presentations. ASSORT demonstrated moderate agreement with the ophthalmologist (κ = 0.54), whereas Rescue showed stronger concordance (κ = 0.85). ASSORT tended to overestimate urgency, assigning more yellow codes than the ophthalmologist. McNemar’s test confirmed significant misclassification by ASSORT (p = 0.0156), while Rescue showed no significant deviation (p = 0.5). Conclusion: While the small sample size limits generalizability, ASSORT shows potential for AI-driven ophthalmic triage but currently overestimates severity compared to the ophthalmologist. Further refinements such as reinforcement learning and multimodal input, as well as large-scale validation are needed to improve accuracy and reduce unnecessary emergency classifications before clinical implementation.
format Article
id doaj-art-5ce35086e59d4b6ebbe033266840b8d6
institution Kabale University
issn 2950-2535
language English
publishDate 2025-10-01
publisher Elsevier
record_format Article
series AJO International
spelling doaj-art-5ce35086e59d4b6ebbe033266840b8d62025-08-20T03:58:35ZengElsevierAJO International2950-25352025-10-012310015910.1016/j.ajoint.2025.100159Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergenciesClaudio Xompero0Lorenzo Rossi1Francesca Amoroso2Antonio Bechara Ghobril3Diana Elena Ionita4Eric H. Souied5Carl-Joe Mehanna6Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Créteil, FranceDepartment of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Créteil, FranceDepartment of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Créteil, FranceDepartment of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Créteil, FranceDepartment of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Créteil, FranceDepartment of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Créteil, FranceCorresponding author at: Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, 40 Avenue de Verdun, 94000 Créteil, France.; Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Créteil, FranceIntroduction: ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage) is a GPT-4-based triage tool designed to assess ophthalmic emergencies using a three-tier color-coded system. This study compares ASSORT to the Rescue triage method, using the ophthalmologist’s final assessment as the reference standard. Materials and methods: A prospective study was conducted at the Créteil University Hospital from April to June 2024. Each patient underwent triage using ASSORT, followed by the Rescue triage method. Both tools used the same color-coding system to stratify severity: yellow for emergency cases, green for urgent cases, and white for non-urgent cases. An examining ophthalmologist in their final year of residency performed the final assessment. Concordance between the ophthalmologist and each of the tools was analyzed using Cohen’s kappa coefficient, alongside precision and recall metrics. Results: Fifty-one patients were included. Case severities were distributed as follows: 22/51 white, 27/51 green, and 2/51 yellow, with conjunctivitis (17.5 %) and corneal abrasions (12.5 %) being the two most common presentations. ASSORT demonstrated moderate agreement with the ophthalmologist (κ = 0.54), whereas Rescue showed stronger concordance (κ = 0.85). ASSORT tended to overestimate urgency, assigning more yellow codes than the ophthalmologist. McNemar’s test confirmed significant misclassification by ASSORT (p = 0.0156), while Rescue showed no significant deviation (p = 0.5). Conclusion: While the small sample size limits generalizability, ASSORT shows potential for AI-driven ophthalmic triage but currently overestimates severity compared to the ophthalmologist. Further refinements such as reinforcement learning and multimodal input, as well as large-scale validation are needed to improve accuracy and reduce unnecessary emergency classifications before clinical implementation.http://www.sciencedirect.com/science/article/pii/S2950253525000620TriageOphthalmic emergenciesLarge language modelsArtificial intelligenceTelemedicine
spellingShingle Claudio Xompero
Lorenzo Rossi
Francesca Amoroso
Antonio Bechara Ghobril
Diana Elena Ionita
Eric H. Souied
Carl-Joe Mehanna
Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergencies
AJO International
Triage
Ophthalmic emergencies
Large language models
Artificial intelligence
Telemedicine
title Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergencies
title_full Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergencies
title_fullStr Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergencies
title_full_unstemmed Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergencies
title_short Pilot study of ASSORT (AI-based Symptom Stratification in Ophthalmology for Rapid Triage): a triage tool for ophthalmic emergencies
title_sort pilot study of assort ai based symptom stratification in ophthalmology for rapid triage a triage tool for ophthalmic emergencies
topic Triage
Ophthalmic emergencies
Large language models
Artificial intelligence
Telemedicine
url http://www.sciencedirect.com/science/article/pii/S2950253525000620
work_keys_str_mv AT claudioxompero pilotstudyofassortaibasedsymptomstratificationinophthalmologyforrapidtriageatriagetoolforophthalmicemergencies
AT lorenzorossi pilotstudyofassortaibasedsymptomstratificationinophthalmologyforrapidtriageatriagetoolforophthalmicemergencies
AT francescaamoroso pilotstudyofassortaibasedsymptomstratificationinophthalmologyforrapidtriageatriagetoolforophthalmicemergencies
AT antoniobecharaghobril pilotstudyofassortaibasedsymptomstratificationinophthalmologyforrapidtriageatriagetoolforophthalmicemergencies
AT dianaelenaionita pilotstudyofassortaibasedsymptomstratificationinophthalmologyforrapidtriageatriagetoolforophthalmicemergencies
AT erichsouied pilotstudyofassortaibasedsymptomstratificationinophthalmologyforrapidtriageatriagetoolforophthalmicemergencies
AT carljoemehanna pilotstudyofassortaibasedsymptomstratificationinophthalmologyforrapidtriageatriagetoolforophthalmicemergencies