{"id":"W4206194534","doi":"10.1002/sta4.450","title":"Sparse Bayesian predictive modelling of tumour response using radiomic features","year":2022,"lang":"en","type":"article","venue":"Stat","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Computer science; Bayesian probability; Feature selection; Bayesian inference; Artificial intelligence; Feature (linguistics); Inference; Machine learning; Model selection; Radiomics; Pattern recognition (psychology); Data mining","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":[0.000830073,0.0001201507,0.0002993005,0.0002049966,0.0002217774,0.000006824948,0.0001116801,0.00002944774,0.0001783973],"category_scores_gemma":[0.0001809617,0.0001144866,0.00009987251,0.0002201475,0.0001190883,0.00004423777,0.00009337981,0.0005980624,0.000001032492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001723297,"about_ca_system_score_gemma":0.0002582875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001718822,"about_ca_topic_score_gemma":4.467822e-7,"domain_scores_codex":[0.9986172,0.0002338272,0.000244567,0.0002356322,0.0004233526,0.0002454135],"domain_scores_gemma":[0.9993358,0.0001501651,0.0001204899,0.0002100782,0.0000437205,0.0001398058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009291629,0.0002681936,0.007977532,0.0001441307,0.0002209376,0.000895794,0.006752657,0.7763106,0.1928301,0.0002743606,0.003440148,0.001593895],"study_design_scores_gemma":[0.001510948,0.000360561,0.003160195,0.00007352811,0.00012473,0.0006532318,0.0009616741,0.9900313,0.001363751,0.0003523969,0.001275267,0.0001324386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8568835,0.0004539997,0.1410001,0.0007871573,0.0002153449,0.0002043156,0.00003163991,0.00004461019,0.0003792749],"genre_scores_gemma":[0.9832841,0.00001804265,0.0156304,0.000295869,0.0000978199,0.000008429297,0.00001834521,0.00003620167,0.0006107893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2137207,"threshold_uncertainty_score":0.4668628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02290875228337112,"score_gpt":0.2906381868352594,"score_spread":0.2677294345518882,"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."}}