{"id":"W2888163428","doi":"10.1016/j.compmedimag.2018.08.008","title":"Efficient multi-kernel multi-instance learning using weakly supervised and imbalanced data for diabetic retinopathy diagnosis","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Artificial intelligence; False positive paradox; Computer science; Diabetic retinopathy; Machine learning; Pattern recognition (psychology); Supervised learning; Semi-supervised learning; Kernel (algebra); Medicine; Diabetes mellitus; Mathematics","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":[0.001034249,0.0002970296,0.000646143,0.0002128748,0.0004305188,0.0001207581,0.0002703833,0.0001055211,0.000009352566],"category_scores_gemma":[0.001271939,0.0002530936,0.0001059523,0.0003798312,0.0009735671,0.00007455184,0.000377581,0.000444177,0.000001507761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001998856,"about_ca_system_score_gemma":0.0000905503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006036197,"about_ca_topic_score_gemma":0.000003943693,"domain_scores_codex":[0.9976148,0.0001339576,0.0004527183,0.000852093,0.0004338109,0.000512635],"domain_scores_gemma":[0.9981345,0.0003814378,0.0001389687,0.0005453912,0.0002593021,0.0005404247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000497421,0.0009731273,0.8212805,0.001481313,0.0004752713,0.0003600556,0.001626366,0.00004671359,0.02344276,0.00009676515,0.0007010567,0.1490187],"study_design_scores_gemma":[0.0048297,0.0001013441,0.01789788,0.001103848,0.0003270966,0.0001261106,0.0001474322,0.9737496,0.0002041066,0.00001555478,0.001216999,0.0002802748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6797589,0.002277955,0.3154192,0.001880341,0.0002452242,0.0002613211,0.00002138027,0.0001298356,0.00000585714],"genre_scores_gemma":[0.9118997,0.0008877956,0.08539152,0.001309389,0.0003146789,0.00001943309,0.0001003014,0.00004619501,0.00003095523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.973703,"threshold_uncertainty_score":0.9999921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04435630286224258,"score_gpt":0.3339190018480665,"score_spread":0.2895626989858239,"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."}}