{"id":"W4399852062","doi":"10.1101/2024.06.19.24308396","title":"Multi-task Bayesian Model Combining FDG-PET/CT Imaging and Clinical Data for Interpretable High-Grade Prostate Cancer Prognosis","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université Laval","funders":"","keywords":"Prostate cancer; Bayesian probability; Medicine; Artificial intelligence; Cancer; Medical physics; Computer science; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002895741,0.00112533,0.00107763,0.001158788,0.0004409426,0.0009544138,0.001383402,0.001345794,0.001690508],"category_scores_gemma":[0.004959953,0.0006588852,0.001174884,0.000671866,0.0006150655,0.001039589,0.0008643413,0.001355917,0.0005994216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001204205,"about_ca_system_score_gemma":0.001447177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01509131,"about_ca_topic_score_gemma":0.01577901,"domain_scores_codex":[0.9990773,0.0003823814,0.00004520353,0.0002495661,0.0001515415,0.00009394551],"domain_scores_gemma":[0.9980147,0.001268242,0.0002327035,0.0001051768,0.00026657,0.0001125512],"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":[0.0005520971,0.0001875144,0.008382533,0.00009132823,0.0001364218,0.0001183515,0.00006953454,0.911997,0.001794092,0.003093443,0.002077632,0.07150003],"study_design_scores_gemma":[0.0000100441,0.00001979559,0.0005354039,0.000005602139,0.00001178778,0.00001353692,0.000002632856,0.9964352,0.0002013451,0.002593962,0.0001641996,0.000006519961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1179613,0.001124429,0.8740014,0.001827614,0.0001205517,0.0001255748,0.001622154,0.00122701,0.00198992],"genre_scores_gemma":[0.9235593,0.0004215013,0.07072862,0.0004089982,0.0001736588,0.0001777906,0.001916262,0.00006725235,0.002546703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01509131,"threshold_uncertainty_score":0.03000695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04486002714107295,"score_gpt":0.3877652017474055,"score_spread":0.3429051746063326,"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."}}