{"id":"W4391018555","doi":"10.1016/j.cmpb.2024.108032","title":"Label correlation guided discriminative label feature learning for multi-label chest image classification","year":2024,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multi-label classification; Discriminative model; Artificial intelligence; Computer science; Pattern recognition (psychology); Feature (linguistics); Correlation; Machine learning; Consistency (knowledge bases); Off-label use; Mathematics; Medicine","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":[0.001550719,0.0002424487,0.0002967606,0.0004314042,0.0001571232,0.0004150955,0.0004636137,0.0002021165,0.000001686143],"category_scores_gemma":[0.0001644512,0.0001883978,0.00003809248,0.001149482,0.0002632634,0.0005537001,0.0002366244,0.0003861817,0.000004578807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007803814,"about_ca_system_score_gemma":0.00003899835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000915622,"about_ca_topic_score_gemma":0.000002204476,"domain_scores_codex":[0.9981841,0.0002128112,0.000391066,0.0007151529,0.0001819443,0.0003148646],"domain_scores_gemma":[0.998867,0.0004247157,0.0001421755,0.000341962,0.0001465302,0.00007762262],"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":[0.000006539624,0.0001425153,0.0003381855,0.000162815,0.00002114679,0.000004418843,0.001380923,6.270926e-7,0.005066037,0.03651741,0.000854081,0.9555053],"study_design_scores_gemma":[0.001387239,0.0004857497,0.003639416,0.0002496698,0.00002329976,0.00001446483,0.0002497347,0.9613413,0.000461662,0.006802787,0.02511247,0.000232163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001132685,0.002338876,0.9848412,0.009161507,0.0008970582,0.0007818499,0.0000021305,0.0007796171,0.00006509711],"genre_scores_gemma":[0.01344983,0.000220287,0.9851663,0.0001098484,0.0001322184,0.0002291552,0.00009174086,0.00001949745,0.0005811063],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9613407,"threshold_uncertainty_score":0.7682638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1867955709494823,"score_gpt":0.4398610810705291,"score_spread":0.2530655101210468,"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."}}