November 18, 2026
Health news, explained with evidence
LIVE
Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine The Role of Daily Mobility Training in Managing Sedentary Tension New Theoretical Framework Explores Memory Formation and Dementia Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine The Role of Daily Mobility Training in Managing Sedentary Tension New Theoretical Framework Explores Memory Formation and Dementia

New AI Model Improves Glaucoma Diagnosis Using Incomplete Patient Data

🔬 Research 1 min read 👁 4

Researchers have developed an AI tool capable of diagnosing glaucoma even when some patient medical records, such as fundus photographs or visual field tests, are missing.

🔬Research

Key points

  • CGMA-Net maintains diagnostic accuracy with incomplete examination data.
  • The model achieved 97.6% accuracy in a retrospective study of over 3,000 participants.
  • Further validation is needed for use in general clinical practice.

A research team has introduced a new artificial intelligence model, CGMA-Net, designed to assist in the diagnosis of glaucoma. Clinical datasets often suffer from incomplete records, where patients may have undergone one type of eye examination but not another. By utilizing gated adaptive fusion, this model can generate diagnostic assessments regardless of whether it receives fundus photography, visual field testing, or both, without the need to estimate or impute missing data.

The study evaluated the model using a retrospective cohort of 5,181 samples from 3,262 participants. Results indicated a high level of accuracy, with an area under the receiver operating characteristic curve of 0.997 and 97.6% overall accuracy. The system maintained strong performance across all tested scenarios, including when only one type of diagnostic input was provided.

What to know: While these findings demonstrate technical feasibility, the study relied on a selected retrospective cohort. The model has not yet been validated in unselected clinical populations that include more ambiguous or complex cases. Patients should always consult with an ophthalmologist for professional diagnosis and personalized care decisions regarding eye health.

Source Nature Health Sciences — nature.com/articles/s41598-026-81016-9 ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.