{"id":"W1987054640","doi":"10.1016/j.radonc.2015.02.015","title":"CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma","year":2015,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":706,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute; National Institutes of Health; KWF Kankerbestrijding; Stichting voor de Technische Wetenschappen; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Health Foundation Limburg","keywords":"Radiomics; Concordance; Medicine; Univariate; Imaging biomarker; Multivariate analysis; Adenocarcinoma; Multivariate statistics; Biomarker; Concordance correlation coefficient; Oncology; Radiology; Internal medicine; Magnetic resonance imaging; Cancer; Computer science; Statistics; Machine learning; Mathematics","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":[0.0008058053,0.0001988623,0.000604814,0.0002407159,0.00004975296,0.00001981845,0.0001089045,0.0001356812,0.00008039721],"category_scores_gemma":[0.0001789462,0.0001601143,0.00007661416,0.0002378465,0.0002200202,0.00006005233,0.00001696615,0.0006495564,0.000002132365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007088712,"about_ca_system_score_gemma":0.0004659311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066906,"about_ca_topic_score_gemma":0.00002580577,"domain_scores_codex":[0.9985113,0.0002189681,0.0003145238,0.0003685027,0.000219689,0.0003669873],"domain_scores_gemma":[0.9990454,0.0001969937,0.00009108772,0.0002244747,0.0000363127,0.0004057267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004214347,0.001233127,0.6805259,0.0004506744,0.0005853885,0.006520309,0.004240428,0.001519457,0.01209109,0.001974699,0.04048109,0.2461635],"study_design_scores_gemma":[0.03998844,0.003754691,0.09967846,0.0002954782,0.0003776147,0.002543953,0.0005250508,0.3835826,0.0008575064,0.0005681909,0.4671346,0.0006933644],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.932064,0.04163034,0.007455545,0.01615029,0.0006214603,0.0005844265,0.00000787711,0.0001007661,0.00138531],"genre_scores_gemma":[0.9852641,0.0006321819,0.008368181,0.005135798,0.000317174,0.00002763652,0.00002962608,0.00003986122,0.0001854238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5808474,"threshold_uncertainty_score":0.6529272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0170700159655151,"score_gpt":0.3163460536078446,"score_spread":0.2992760376423295,"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."}}