{"id":"W2900695129","doi":"10.1109/trpms.2018.2878934","title":"Comparison of Radiomics Models Built Through Machine Learning in a Multicentric Context With Independent Testing: Identical Data, Similar Algorithms, Different Methodologies","year":2018,"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":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Radiomics; Random forest; Computer science; Machine learning; Robustness (evolution); Artificial intelligence; Classifier (UML); Feature selection; Context (archaeology); Data mining; Algorithm","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":[0.001578477,0.0001830817,0.0005000231,0.0002460428,0.0002897679,0.00004590825,0.0002825976,0.0001410828,0.00009937012],"category_scores_gemma":[0.0009928434,0.000123809,0.00003534732,0.0005728039,0.001167124,0.0002461071,0.00001075926,0.0008188919,0.000002236741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005157664,"about_ca_system_score_gemma":0.0002083141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005665771,"about_ca_topic_score_gemma":0.0002963819,"domain_scores_codex":[0.9973903,0.0002881865,0.000540708,0.0004774806,0.0009937806,0.0003095047],"domain_scores_gemma":[0.9975843,0.001731478,0.0001766499,0.0001883119,0.00006043672,0.0002587781],"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":[0.0005183619,0.001058242,0.08650873,0.0001465088,0.0001514609,0.00005975289,0.003590444,0.04707538,0.0004022419,0.0004533839,0.00009818479,0.8599373],"study_design_scores_gemma":[0.002289416,0.0009915476,0.00479798,0.0001808558,0.0000881216,0.00008831009,0.0006416859,0.9889036,0.001505112,0.0001453017,0.0002332622,0.0001348498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4676399,0.0002467055,0.5285863,0.002963881,0.0001901014,0.0002066902,0.00000971091,0.00004643656,0.0001102063],"genre_scores_gemma":[0.972522,0.0004192356,0.02660951,0.0003292774,0.00006528562,0.00000757318,0.00001203659,0.00001077789,0.00002430554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9418282,"threshold_uncertainty_score":0.5048786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1820891429310312,"score_gpt":0.4121424549542282,"score_spread":0.230053312023197,"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."}}