Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Co-Annotator: Expert-Distilled ViT and VLM for Visual and Documentation Guidance in Age-Related Macular Degeneration

Ziheng "Leo" Li, Benjamin Freeman, Akshay Raman, Kavin Aravindhan Rajkumar +4 more

Published

Aug 31, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Aug 31, 2026

Open arXiv Open DOI Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Expert Verification Medicine

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write. We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that pre-fills editable biomarker summaries for retinal optical coherence tomography (OCT). We first collect expert gaze and dictations (US1) to train the models, significantly improving diagnostic accuracy and biomarker generation. We then deploy the system with ophthalmology residents: a controlled resident study (US2) confirmed each modality is safe and independently beneficial, with AOI guidance producing lasting perceptual efficiency gains through post-guidance carryover and VLM guidance more than doubling biomarker documentation breadth. In a combined deployment across two academic institutions (US3), providing both modalities simultaneously produced efficiency gains that substantially exceeded either modality alone: correct diagnoses per minute increased by 40% and comment editing time fell by 67%, without compromising diagnostic accuracy. Notably, neither modality improved efficiency during guidance in US2, which makes the in-guidance efficiency gain under combined guidance in US3 the more striking result. Expert-distilled multimodal guidance can remove two distinct clinical workflow bottlenecks at once (visual search overhead and documentation burden) without compromising the diagnostic accuracy clinicians already achieve.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Expert Verification

Directly usable for protocol triage.

"Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write."

Reported Metrics

strong

Accuracy, Coherence

Useful for evaluation criteria comparison.

"We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that pre-fills editable biomarker summaries for retinal optical coherence tomography (OCT)."

Rater Population

strong

Domain Experts

Helpful for staffing comparability.

"We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that pre-fills editable biomarker summaries for retinal optical coherence tomography (OCT)."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

accuracycoherence
Human feedback details
Uses human feedback
Yes
Feedback types
Expert Verification
Rater population
Domain Experts
Expertise required
Medicine
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write.
  • We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that pre-fills editable biomarker summaries for retinal optical coherence tomography (OCT).
  • We first collect expert gaze and dictations (US1) to train the models, significantly improving diagnostic accuracy and biomarker generation.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Expert verification evaluation Crowd/annotator signal evaluation Accuracy

Contribution summary

  • We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that…
  • We first collect expert gaze and dictations (US1) to train the models, significantly improving diagnostic accuracy and biomarker generation.
  • In a combined deployment across two academic institutions (US3), providing both modalities simultaneously produced efficiency gains that substantially exceeded either modality alone: correct diagnoses per minute increased by 40% and comment…

Why it matters for eval

  • We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that…

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Expert Verification

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: accuracy, coherence