Post

New research · Ophthalmology
NPJ digital medicine · 6d
StudyNPJ digital medicine · 2025

Clinically informed semi-supervised learning improves disease annotation and equity from electronic health records: a glaucoma case study.

Mousa Moradi, Rishi Shah, Asahi Fujita … Nazlee Zebardast
Read paper
OphthalmologyStudy

Ci-SSGAN improved glaucoma label accuracy versus ICD-based labels.

Clinically informed semi-supervised learning improves disease annotation and equity from electronic health records: a glaucoma case study.

Mousa Moradi … Nazlee Zebardast
NPJ digital medicine · 2025
Results

better at distinguishing patients with glaucoma from those without it

Ci-SSGAN
0.95AUROC
ICD-based labels
0.85AUROC
More results

These limitations constrain the accuracy of datasets used to investigate disease pathogenesis and progression and to develop robust artificial intelligence (artificial intelligence) systems.

More results

To address this challenge, we introduce Ci-SSGAN (Clinically Informed Semi-Supervised Generative Adversarial Network), a novel framework that leverages large-scale unlabeled clinical text to reannotate patient conditions with improved accuracy and equity.

“
Conclusion

By integrating semi-supervised learning and demographic conditioning, Ci-SSGAN minimizes reliance on expert annotations, making artificial intelligence development more accessible to resource-constrained healthcare systems.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
0·962 for OCT
MerMED-FM was very accurate at diagnosing diseases using eye scans
AI / Informatics
0.98
Artificial intelligence's eyelid-height measurements matched doctors' manual measurements almost perfectly
AI / Informatics
92.1%
combining eye scans and photos correctly told benign from cancerous lesions apart nearly every time
Cohort Study
28.6%
recurred locally in more than 1 in 4 patients over years of follow-up
Cohort Study
-0.395
excision group's post-op eyelid fullness score was lower - greater improvement
Cohort Study
86.7%
of infants probed after 12 months still had unresolved tear duct blockage
Observational
16%
eyelid tissue in rosacea patients showed less of this key repair-signaling protein inside cell nuclei
Cohort Study
25%
about 1 in 4 treated cases had symptoms return after improving