{"id":"W3007829463","doi":"10.1177/0846537119899526","title":"Radiogenomic Models Using Machine Learning Techniques to Predict EGFR Mutations in Non-Small Cell Lung Cancer","year":2020,"lang":"en","type":"article","venue":"Canadian Association of Radiologists Journal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Jewish General Hospital; McMaster University; McGill University Health Centre; University of Calgary","funders":"Réseau de cancérologie Rossy; McGill University","keywords":"Radiogenomics; Medicine; Lung cancer; Epidermal growth factor receptor; Contouring; Nuclear medicine; Exon; Logistic regression; Cancer; Radiology; Radiomics; Oncology; Internal medicine; Gene; Biology","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":[0.0009628803,0.000165438,0.0004690537,0.000478418,0.0001660233,0.00004289889,0.0001805144,0.0001691407,0.00005778204],"category_scores_gemma":[0.001006041,0.0001664371,0.0001246884,0.0004043971,0.00003789205,0.0001027984,0.00002068016,0.00111738,0.000001584068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002900759,"about_ca_system_score_gemma":0.001243942,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01832487,"about_ca_topic_score_gemma":0.004500303,"domain_scores_codex":[0.9983405,0.0001801367,0.0005502574,0.0002297103,0.0002343266,0.0004650865],"domain_scores_gemma":[0.9983132,0.0001037738,0.0004259559,0.0000860441,0.0001828729,0.0008881685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000429876,0.00002427787,0.8387288,0.00007662439,0.0001247792,0.0001766191,0.002370443,0.1393756,0.01288006,0.00002492371,0.002798798,0.003376097],"study_design_scores_gemma":[0.001762742,0.000236615,0.03190925,0.000279653,0.0001927969,0.0001626926,0.0002181972,0.9593205,0.0008610845,0.000067363,0.004709644,0.0002794626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9427162,0.001053609,0.03618605,0.01802049,0.0002520794,0.0005778029,0.00005752841,0.00004845453,0.001087727],"genre_scores_gemma":[0.9796526,0.0005190779,0.01644306,0.002655938,0.0004481572,0.00001140206,0.00002954187,0.00003718616,0.0002030524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8199449,"threshold_uncertainty_score":0.9882122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01758956021471287,"score_gpt":0.2806511289239781,"score_spread":0.2630615687092653,"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."}}