{"id":"W2088210810","doi":"10.1118/1.4915284","title":"Bayesian network ensemble as a multivariate strategy to predict radiation pneumonitis risk","year":2015,"lang":"en","type":"article","venue":"Medical Physics","topic":"Effects of Radiation Exposure","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal General Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Western Canada Research Grid","keywords":"Multivariate statistics; Radiation Pneumonitis; Bayesian probability; Multivariate analysis; Bayesian network; Computer science; Medical physics; Econometrics; Statistics; Artificial intelligence; Medicine; Radiation therapy; Machine learning; Mathematics; Radiology","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":[0.0007390524,0.0002132791,0.0003824837,0.00004743014,0.00008706906,0.00003089919,0.0001531155,0.0002171831,0.0001164258],"category_scores_gemma":[0.001898881,0.0001916212,0.00008867591,0.0004422841,0.00006006177,0.0001196154,0.00005184928,0.0004844623,0.0005893601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001467136,"about_ca_system_score_gemma":0.0006233383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002531603,"about_ca_topic_score_gemma":0.00001788143,"domain_scores_codex":[0.9975197,0.0001646585,0.0003295997,0.0003534616,0.001190218,0.0004423589],"domain_scores_gemma":[0.9976733,0.0002567191,0.0001333423,0.0003801898,0.000154398,0.001402003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005140481,0.0005901695,0.05576195,0.00008748675,0.0002841019,0.0003142257,0.001646992,0.01021316,0.0004188866,0.001931563,0.09690402,0.8313334],"study_design_scores_gemma":[0.05185535,0.02712628,0.4662203,0.00193235,0.002230658,0.0005817417,0.0008293047,0.1995714,0.01852763,0.1254652,0.1018428,0.003817081],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.663368,0.0006444316,0.2704864,0.008827829,0.002362932,0.002840899,0.00005425628,0.0009251975,0.05049007],"genre_scores_gemma":[0.9930997,0.00003596246,0.0007889953,0.00211347,0.003460069,0.00005291983,0.00009541002,0.00004837713,0.0003050999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8275163,"threshold_uncertainty_score":0.7814085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01519666457139939,"score_gpt":0.2922846864418145,"score_spread":0.2770880218704151,"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."}}