{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005415646,0.0007350893,0.001103728,0.002447321,0.00100201,0.001765176,0.00119674,0.0014404,0.001365434],"category_scores_gemma":[0.01726882,0.0002697647,0.0008965365,0.002274697,0.001269992,0.001807643,0.001721813,0.001873044,0.0007171661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006871055,"about_ca_system_score_gemma":0.001135486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009825587,"about_ca_topic_score_gemma":0.0008746302,"domain_scores_codex":[0.9975957,0.0009999267,0.000177763,0.0005378913,0.0005298884,0.0001586969],"domain_scores_gemma":[0.993495,0.00360841,0.0008067014,0.0009219921,0.0009532981,0.0002146721],"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":[0.0005858224,0.0003198982,0.02682468,0.0004061669,0.0001957857,0.0005724767,0.0005287989,0.1678811,0.007699407,0.08214486,0.02039997,0.692441],"study_design_scores_gemma":[0.00001671984,0.0000918654,0.00458247,0.00004908917,0.00002414902,0.0002700443,0.0001196475,0.9240052,0.001664832,0.06493822,0.00420683,0.00003098307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02903996,0.000713818,0.9672573,0.001269241,0.0001775578,0.00006841724,0.000354639,0.0003363978,0.0007825855],"genre_scores_gemma":[0.5806289,0.001218977,0.4117379,0.0005848628,0.0007406054,0.0003936562,0.00161503,0.0001243724,0.002955709],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005415646,"threshold_uncertainty_score":0.02864105,"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."}}