{"id":"W3105017984","doi":"10.1007/978-3-030-58589-1_12","title":"EGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma Diagnosis","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Curriculum; Glaucoma; Artificial intelligence; CAD; Debiasing; Machine learning; Fundus (uterus); Process (computing); Sensitivity (control systems); Class (philosophy); Categorization; Dual (grammatical number); Ophthalmology; Medicine; Engineering drawing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003868151,0.0004348955,0.000764567,0.0004325759,0.000237986,0.0001744972,0.0005476703,0.0002826292,0.00004513288],"category_scores_gemma":[0.0007178889,0.0003683137,0.0002915495,0.000518289,0.0004790819,0.0001428263,0.0001847088,0.001331657,0.00002219246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001687428,"about_ca_system_score_gemma":0.0002481637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004625982,"about_ca_topic_score_gemma":0.00001437247,"domain_scores_codex":[0.9972828,0.00003605505,0.0003760591,0.001203493,0.0006478026,0.000453801],"domain_scores_gemma":[0.997912,0.0007261273,0.0002448451,0.0005028071,0.0003022748,0.0003119136],"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":[0.000178098,0.0002064006,0.02875686,0.0002723602,0.0001866573,0.0004824727,0.001362194,0.008755643,0.0001472958,0.0118357,0.0001147314,0.9477016],"study_design_scores_gemma":[0.0007238713,0.002800092,0.001146584,0.003334404,0.0004202089,0.00007097968,0.00000663177,0.8964891,0.001285513,0.08653128,0.006149569,0.001041708],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001747628,0.0004772468,0.9934517,0.002783567,0.0003109107,0.0004313804,0.000007198194,0.0001429458,0.0006474094],"genre_scores_gemma":[0.5233013,0.00007321258,0.4718236,0.003198623,0.001249919,0.00003637933,0.00004516109,0.00007144614,0.0002003717],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9466599,"threshold_uncertainty_score":0.9998769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02487421734547697,"score_gpt":0.2967810849737178,"score_spread":0.2719068676282408,"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."}}