Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2232
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-24T00:00:53.166054Z
status: published
lens: g_space
sector: health
headline: An Agentic AI Workflow for Automated Macular Hole Diagnosis and Structured Report Generation
dek: Introduction: Current AI models for optical coherence tomography (OCT) primarily focus on diagnosis as a standalone task. We developed and validated an end-to-end agentic AI workflow that integrates automated macular hole (MH) diagnosis from OCT images with structured patient-friendly report generation.
Methods: The proposed sequential workflow coordinated by a workflow orchestration agent consisted of an image diagnosis stage and a language generation step. The OCT version of RETFound, a self-supervised retinal…
gain_title: A fine-tuned retinal foundation model detected macular holes on external OCT datasets with high accuracy, while a language model produced standardized patient-friendly reports without influencing the diagnosis.
problem_title: (none)
trace_subject: (none)
gain_reading: A fine-tuned retinal foundation model detected macular holes on external OCT datasets with high accuracy, while a language model produced standardized patient-friendly reports without influencing the diagnosis.
gain_evidence: On external validation (n = 1014), accuracy was 98.8% (95% CI 97.9-99.3%) | generated concise and standardized patient-friendly reports for all samples, without the language model influencing diagnostic decisions
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built a two-stage workflow coordinated by an orchestration agent. A fine-tuned version of the RETFound retinal foundation model first classifies each OCT scan as macular hole or normal macula. The result is then placed into a structured prompt, and GPT-4 writes a clinical report.

The design matters because it keeps diagnosis separate from text generation, so the language model does not decide the diagnosis. The authors describe it as a practical, scalable option for virtual vitreoretinal clinics, but the evidence comes from public datasets and a binary task, so real-world clinical performance is not yet shown.
limitation: The task was a binary classification of macular hole versus normal macula using public OCT datasets, so the study does not show how the workflow performs on other retinal conditions or in live clinical use.
tag: Evidence-backed gain
key_points: The workflow combines an image diagnosis stage with a language generation step, coordinated by an orchestration agent. | On the internal test set of 180 scans, accuracy was 100% with an AUC of 1.00. | On external validation of 1014 scans, sensitivity was 97.9%, specificity was 100%, and AUC was 0.999. | Grad-CAM analysis showed predictions were driven by relevant retinal regions, particularly the macular hole and adjacent layers.
rundown: The diagnostic stage used the OCT version of RETFound, a self-supervised retinal foundation model, fine-tuned for binary classification of macular OCT scans as macular hole or normal macula. Training, validation and internal testing used multiple public OCT datasets with patient-level stratified splitting.

Performance was checked on two independent external datasets using accuracy, sensitivity, specificity and ROC AUC. Grad-CAM heat maps were used to examine which image regions drove predictions.

For each new image, the agent passed the classifier's output into a structured prompt and called GPT-4 to write the report. The study reports that reports were concise and standardized for all samples.
sources:
- peer_reviewed | Ophthalmology and Therapy | https://doi.org/10.1007/s40123-026-01523-w | 2026-10-23
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

64e04cf50acf99888a54f165ecaedad65d4b64c9b349a564a59e534062041d0a

previous

0000000000000000000000000000000000000000000000000000000000000000