{"id":"W2047103489","doi":"10.1088/0031-9155/54/18/s02","title":"Predicting radiotherapy outcomes using statistical learning techniques","year":2009,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Bivariate analysis; Computer science; Artificial intelligence; Support vector machine; Machine learning; Resampling; Nonlinear system; Logistic regression; Artificial neural network; Pattern recognition (psychology); Kernel (algebra); 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":[0.0004833872,0.0001549576,0.0005283153,0.0001121975,0.00007273838,0.000006388866,0.00005583655,0.00009044398,0.00002478631],"category_scores_gemma":[0.0005147108,0.0001066823,0.00002994001,0.0001502065,0.0002771145,0.00003651875,0.00001835512,0.0006563638,4.370501e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004100669,"about_ca_system_score_gemma":0.0000309839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001428412,"about_ca_topic_score_gemma":9.05931e-7,"domain_scores_codex":[0.9989716,0.00009441637,0.0002916008,0.0002650082,0.0001001202,0.0002772008],"domain_scores_gemma":[0.9994059,0.0002674171,0.00007730564,0.0001090344,0.00003062541,0.0001096824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005179006,0.00007804167,0.682899,0.0000333288,0.000035966,0.00003685925,0.0004332168,0.00002894863,0.03954536,0.008310848,0.00007809595,0.2684685],"study_design_scores_gemma":[0.01285632,0.008890059,0.4525539,0.001888557,0.0004638302,0.0008098875,0.001263361,0.4165375,0.001726857,0.07833102,0.02349709,0.001181607],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8436076,0.001147407,0.1425525,0.01017379,0.0001558983,0.0002785597,0.000001473765,0.0001506023,0.001932144],"genre_scores_gemma":[0.9675174,0.0005889261,0.02694281,0.00416707,0.0007050695,0.000003204696,0.00002469158,0.00001514687,0.00003567518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4165086,"threshold_uncertainty_score":0.4350379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1062175260067964,"score_gpt":0.446842933508717,"score_spread":0.3406254075019205,"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."}}