{"id":"W4406999711","doi":"10.1016/j.xops.2025.100721","title":"Code-Free Deep Learning Glaucoma Detection on Color Fundus Images","year":2025,"lang":"en","type":"article","venue":"Ophthalmology Science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre intégré universitaire de santé et de services sociaux de l'Est-de-l'Île-de-Montréal; McGill University; Centre Hospitalier de l’Université de Montréal; Université de Montréal; University of Toronto; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Hôpital Maisonneuve-Rosemont","funders":"","keywords":"Computer science; Fundus (uterus); Artificial intelligence; Glaucoma; Computer vision; Code (set theory); Optometry; Ophthalmology; Medicine; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000628894,0.0001114053,0.000215178,0.0004068531,0.0004426633,0.00004609454,0.0003035029,0.00006319112,0.00008791922],"category_scores_gemma":[0.001400016,0.00009344972,0.00007036497,0.001232452,0.0008117674,0.00009855885,0.0001136749,0.0003297634,0.00008593027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009857643,"about_ca_system_score_gemma":0.0001051518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005187466,"about_ca_topic_score_gemma":0.000001489788,"domain_scores_codex":[0.9987579,0.00006792256,0.0001588205,0.0004393055,0.0002517636,0.0003242645],"domain_scores_gemma":[0.9991628,0.0001396961,0.00006429698,0.0003852041,0.0001556205,0.00009240671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003117477,0.0002169762,0.5519445,0.00004918719,0.00006369071,0.001001984,0.0001081953,0.0001448921,0.4081519,0.0005867305,0.0002604244,0.03715982],"study_design_scores_gemma":[0.0009667877,0.001209966,0.8276631,0.0001210272,0.0001601753,0.002784456,0.0004168729,0.01588099,0.1484057,0.0009857687,0.001195832,0.000209394],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9450605,0.0001053309,0.0009479714,0.001854487,0.0002510233,0.00008605149,6.724003e-7,0.00006335575,0.05163062],"genre_scores_gemma":[0.9862449,0.000007041215,0.0007417243,0.0002613814,0.00003614511,0.00001048804,0.000001318312,0.000005546763,0.01269141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2757186,"threshold_uncertainty_score":0.3810769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01386871719955626,"score_gpt":0.323889573382254,"score_spread":0.3100208561826978,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}