{"id":"W2909587126","doi":"10.1109/trpms.2019.2893860","title":"Creating Robust Predictive Radiomic Models for Data From Independent Institutions Using Normalization","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Research Institute","keywords":"Normalization (sociology); Standardization; Feature selection; Artificial intelligence; Computer science; Pattern recognition (psychology); Feature (linguistics); Data mining; Logistic regression; Outlier; Machine learning","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":[0.0008087641,0.0001308381,0.0002230478,0.0001931777,0.0005092944,0.00007805599,0.0002106261,0.0001406442,0.0003003914],"category_scores_gemma":[0.0001603342,0.0001080499,0.00004625477,0.0002886124,0.0002576871,0.0005434325,0.000005102689,0.000325585,0.000008005579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008268651,"about_ca_system_score_gemma":0.0005190839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004656435,"about_ca_topic_score_gemma":0.00004653357,"domain_scores_codex":[0.9982536,0.00006165704,0.0003037883,0.0004756506,0.000679881,0.0002254187],"domain_scores_gemma":[0.9989163,0.00044181,0.00009934391,0.0002044388,0.00003835912,0.000299732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002223,0.0002233139,0.002758938,0.00006006122,0.0001192524,0.000007186177,0.0006302429,0.9333106,0.0005533975,0.001145726,0.0001803687,0.06078864],"study_design_scores_gemma":[0.001712932,0.0002187757,0.0004311544,0.0001510125,0.0001066336,0.0000553171,0.0001669547,0.9960631,0.0002256186,0.0001604927,0.0005923493,0.0001156325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3400244,0.00006106821,0.6573608,0.001060781,0.0005191028,0.000342678,0.00007898259,0.00004245399,0.0005097151],"genre_scores_gemma":[0.9884034,0.0002580066,0.01038272,0.0005663773,0.0001527832,0.00001495431,0.0001317654,0.00001076648,0.00007919518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.648379,"threshold_uncertainty_score":0.4406147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08403753685768459,"score_gpt":0.3391682313430357,"score_spread":0.2551306944853511,"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."}}