{"id":"W2809364338","doi":"10.1007/s11517-018-1858-4","title":"Prediction of survival with multi-scale radiomic analysis in glioblastoma patients","year":2018,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":86,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; McGill University Health Centre","funders":"","keywords":"Random forest; Radiomics; Univariate; Glioblastoma; Artificial intelligence; Fluid-attenuated inversion recovery; Correlation; Correlation coefficient; Rank correlation; Pattern recognition (psychology); Progression-free survival; Estimator; Medicine; Mathematics; Computer science; Multivariate statistics; Statistics; Magnetic resonance imaging; Oncology; Overall survival; Radiology","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":[0.0008184771,0.0002032897,0.0006852408,0.0003458304,0.0000464796,0.000009319132,0.0001809246,0.0002047502,0.0001506182],"category_scores_gemma":[0.001097185,0.0001389764,0.0001334557,0.001092008,0.0002837231,0.0000281026,0.0001024004,0.000607529,0.000008096707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007420943,"about_ca_system_score_gemma":0.00004565141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006607215,"about_ca_topic_score_gemma":0.00001022125,"domain_scores_codex":[0.998028,0.00007277169,0.0005616657,0.0004041651,0.0005218051,0.0004115803],"domain_scores_gemma":[0.9990276,0.0002333665,0.0001098007,0.0001982914,0.0001091555,0.0003218022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001234677,0.0002990964,0.9861789,0.00004592954,0.0001704921,0.00002785141,0.0001533498,0.002883962,0.0009900469,0.00001633398,0.00001406888,0.009096535],"study_design_scores_gemma":[0.001379352,0.0005060036,0.5250618,0.0001614136,0.00006295115,0.00001085363,0.00001219956,0.4725089,0.0001068277,8.359973e-7,0.0001107019,0.00007807801],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8375807,0.00004131789,0.1616894,0.0001223842,0.0002093231,0.0001404804,0.000003399463,0.00009747775,0.0001154548],"genre_scores_gemma":[0.9883086,0.00001039519,0.01122902,0.0001181648,0.0002730465,0.000003144046,0.00002898391,0.00001836193,0.00001029595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.469625,"threshold_uncertainty_score":0.5667292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01216833625535062,"score_gpt":0.252875117010992,"score_spread":0.2407067807556414,"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."}}