{"id":"W2912777662","doi":"10.1016/j.ejrad.2019.02.006","title":"Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features","year":2019,"lang":"en","type":"article","venue":"European Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; National Natural Science Foundation of China; Danmarks Frie Forskningsfond; Memorial Sloan-Kettering Cancer Center","keywords":"Medicine; Colorectal cancer; Radiology; Colonic disease; Positron emission tomography; Nuclear medicine; Oncology; Internal medicine; Cancer","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":[0.001126622,0.0001729337,0.0005303044,0.0001876902,0.00008343278,0.00001823253,0.0001682868,0.00002221211,0.00002857271],"category_scores_gemma":[0.0008287632,0.0001146446,0.0001401864,0.00009127757,0.0001145475,0.00009977731,0.00003202458,0.0005508147,0.00001021967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004788158,"about_ca_system_score_gemma":0.0001248165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002071226,"about_ca_topic_score_gemma":2.464889e-7,"domain_scores_codex":[0.9985103,0.0003670494,0.0004602824,0.0001969843,0.0002098901,0.0002555044],"domain_scores_gemma":[0.9986732,0.0002845816,0.0004557366,0.0001238422,0.0002833384,0.0001792829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006548058,0.000581795,0.9340221,0.0004043802,0.001316697,0.004253816,0.001040327,0.02633364,0.00515273,0.0006024608,0.006054692,0.01368929],"study_design_scores_gemma":[0.04303113,0.03598545,0.562664,0.001670265,0.00210681,0.06898189,0.0004427743,0.2801631,0.0001674032,0.0002366845,0.003453637,0.001096786],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819222,0.0004754667,0.01609105,0.0002749682,0.0003772209,0.0003960691,0.000005896798,0.00001883978,0.0004382645],"genre_scores_gemma":[0.9580454,0.00002594906,0.0410642,0.0003089066,0.0004022977,0.000001658556,0.00003334829,0.00005377029,0.00006453704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3713581,"threshold_uncertainty_score":0.4675073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008174993567951507,"score_gpt":0.2379789694230534,"score_spread":0.2298039758551019,"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."}}