{"id":"W2075372833","doi":"10.1118/1.3352709","title":"Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy","year":2010,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Missing data; Support vector machine; Data set; Artificial intelligence; Lung cancer; Radiation therapy; Machine learning; Bayesian network; Medicine; Bayesian probability; Statistics; Computer science; Mathematics; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003424236,0.0001506334,0.0005104243,0.00003842985,0.00004743278,0.00000847928,0.00007862258,0.000102267,0.00009644224],"category_scores_gemma":[0.00008688412,0.0001137687,0.00004728312,0.0001723786,0.0002206017,0.0000639472,0.000017387,0.0006016486,1.482036e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003814999,"about_ca_system_score_gemma":0.0001268055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000230187,"about_ca_topic_score_gemma":0.00007996352,"domain_scores_codex":[0.9986311,0.00003534672,0.0003287897,0.0002443375,0.0004902696,0.0002702189],"domain_scores_gemma":[0.9992726,0.0001300424,0.0001160873,0.0001443876,0.00007968143,0.0002571972],"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":[0.0004339136,0.0004125279,0.9753663,0.0001462088,0.00008950473,0.000003422439,0.0002721436,0.0009286441,0.0002281507,0.000450599,0.0007629518,0.02090565],"study_design_scores_gemma":[0.008604992,0.000612029,0.09141312,0.0002318928,0.0001182076,0.000002738939,0.000009905038,0.898181,0.0002476391,0.000203623,0.000240426,0.0001344781],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9000403,0.0001401445,0.09737968,0.0007955268,0.0004091137,0.0006940561,0.00003836882,0.00004666595,0.0004561896],"genre_scores_gemma":[0.9974138,0.00003948144,0.001412028,0.0002028846,0.0006532572,0.00004066992,0.0001560063,0.00003911378,0.00004274365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8972523,"threshold_uncertainty_score":0.4639352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009492886713867414,"score_gpt":0.311482474445935,"score_spread":0.3019895877320676,"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."}}