{"id":"W4281383153","doi":"10.1002/sim.9442","title":"A classification for complex imbalanced data in disease screening and early diagnosis","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001010537,0.00009939364,0.0001950617,0.0002439733,0.000115556,0.00003056076,0.001067551,0.0000166194,0.00001979096],"category_scores_gemma":[0.001027688,0.0001034553,0.000005429885,0.0004477252,0.0001122145,0.0002306793,0.0005856226,0.0001722679,4.535129e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007822986,"about_ca_system_score_gemma":0.000050393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001322962,"about_ca_topic_score_gemma":0.00004851495,"domain_scores_codex":[0.9984828,0.000116466,0.000372499,0.0005070894,0.0003208923,0.0002002495],"domain_scores_gemma":[0.998078,0.0006843539,0.0001452913,0.0009665379,0.00004765983,0.00007816916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000107182,0.0002057926,0.3139416,0.0001400027,0.00001107001,0.00005131754,0.001604911,0.00003923349,0.0008462445,0.4636994,0.04675098,0.1726022],"study_design_scores_gemma":[0.0008369184,0.0001000932,0.6462744,0.00003898592,0.00000557573,0.000001362698,0.0001062768,0.3175638,0.000004062044,0.02267299,0.01228503,0.0001104662],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001564775,0.0001533494,0.9916396,0.004532844,0.00008178708,0.0005435731,0.001377084,0.00006998813,0.00003706255],"genre_scores_gemma":[0.5261646,0.0001067497,0.4714188,0.0004083291,0.00003047299,0.0006178276,0.001226231,0.000009662618,0.00001734355],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5245999,"threshold_uncertainty_score":0.4218785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1130163235397242,"score_gpt":0.3732825950494658,"score_spread":0.2602662715097416,"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."}}