{"id":"W2001652071","doi":"10.1016/j.compmedimag.2013.12.003","title":"Ensemble-based hybrid probabilistic sampling for imbalanced data learning in lung nodule CAD","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; China Scholarship Council; National Natural Science Foundation of China; Simon Fraser University; University of Alberta","keywords":"Probabilistic logic; Artificial intelligence; Pattern recognition (psychology); Subspace topology; CAD; Computer science; Dimensionality reduction; Sampling (signal processing); Nodule (geology); Computer-aided diagnosis; Probabilistic classification; Statistics; Mathematics; Machine learning; Support vector machine; Computer vision; Naive Bayes classifier; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001100133,0.0002173795,0.0003356268,0.0002470446,0.0001843126,0.0003519081,0.001626681,0.00007562842,0.000003880598],"category_scores_gemma":[0.0009865693,0.000207037,0.00004264584,0.000400836,0.0002115931,0.0006619929,0.000697949,0.0004568469,0.000002959907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003653234,"about_ca_system_score_gemma":0.0001775678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000526363,"about_ca_topic_score_gemma":0.000004549683,"domain_scores_codex":[0.9976662,0.0001321358,0.0004768989,0.0008535998,0.00039622,0.0004748935],"domain_scores_gemma":[0.9976183,0.0007789916,0.000154882,0.001045536,0.0001594001,0.0002428996],"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":[0.00005117663,0.0004780125,0.02256775,0.001149816,0.00005156411,0.00006547818,0.0003592568,0.0002167806,0.007911149,0.04032156,0.01777372,0.9090537],"study_design_scores_gemma":[0.001108053,0.00002412905,0.003731483,0.0002243106,0.000005922485,0.00002262792,0.000005649225,0.9837611,0.0002295629,0.005922999,0.004714395,0.0002497405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00708069,0.0002033744,0.9852765,0.005944524,0.0002533281,0.0006397925,0.0000188783,0.0005615841,0.00002137627],"genre_scores_gemma":[0.5593461,0.0001001313,0.4375786,0.002186686,0.0001081946,0.0002192309,0.0004246397,0.00002673649,0.000009689917],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9835443,"threshold_uncertainty_score":0.8442723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03378149451165669,"score_gpt":0.3051422654233574,"score_spread":0.2713607709117007,"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."}}