{"id":"W4416032068","doi":"10.1007/s10792-025-03771-4","title":"An extensive analysis of machine learning techniques for identifying glaucoma","year":2025,"lang":"en","type":"article","venue":"International Ophthalmology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Glaucoma; Optical coherence tomography; Blindness; Reliability (semiconductor); Fundus (uterus); Field (mathematics); Clinical Practice","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002429705,0.000832005,0.0005962776,0.003525034,0.0005434181,0.0009049515,0.0003872424,0.000582476,0.001858754],"category_scores_gemma":[0.008857664,0.0001680868,0.001332562,0.002153626,0.0002361248,0.0009020533,0.0004071592,0.0007563946,0.0007298785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003901824,"about_ca_system_score_gemma":0.0006095039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00266471,"about_ca_topic_score_gemma":0.003201123,"domain_scores_codex":[0.9983084,0.0003992525,0.0001354184,0.0001820877,0.0008971212,0.00007767339],"domain_scores_gemma":[0.9907142,0.006845889,0.000297771,0.0006464001,0.001437893,0.00005788447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003234615,0.0003951326,0.02323237,0.0004904861,0.0005043806,0.0002727135,0.0000778404,0.05500566,0.01375367,0.003661019,0.008001604,0.8942817],"study_design_scores_gemma":[0.0000403241,0.0009813242,0.1677497,0.0003104658,0.0006575231,0.001513881,0.0002695821,0.7477432,0.03935291,0.01450065,0.0267751,0.0001052532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5140437,0.04159321,0.418894,0.002532986,0.0004983665,0.0002820042,0.004268258,0.001476865,0.01641053],"genre_scores_gemma":[0.8294603,0.01031412,0.1455801,0.0002845835,0.0003859944,0.00009902564,0.005134899,0.0001385072,0.008602516],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003525034,"threshold_uncertainty_score":0.01284969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02851651793216621,"score_gpt":0.4069417508140094,"score_spread":0.3784252328818432,"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."}}