{"id":"W4394460053","doi":"10.6084/m9.figshare.21786980","title":"Feasibility of machine learning-based modeling and prediction using multiple centers data to assess intrahepatic cholangiocarcinoma outcomes","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Cholangiocarcinoma and Gallbladder Cancer Studies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Intrahepatic Cholangiocarcinoma; Computer science; Machine learning; Artificial intelligence; Data science; Medicine; 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":[0.01073109,0.001188841,0.0008960916,0.00188648,0.000583954,0.00170091,0.001300435,0.0006347101,0.001641516],"category_scores_gemma":[0.02025253,0.0003936581,0.00174147,0.001210907,0.0003154733,0.001192805,0.001192591,0.001248254,0.0004491456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008481478,"about_ca_system_score_gemma":0.001610126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009538366,"about_ca_topic_score_gemma":0.006270886,"domain_scores_codex":[0.9961444,0.002372413,0.0002357596,0.0007486031,0.0003166902,0.0001821086],"domain_scores_gemma":[0.9901595,0.006611224,0.0008114607,0.001082686,0.001045135,0.0002901095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008846732,0.0007012323,0.4523633,0.0001431684,0.001096175,0.0003059793,0.0002999562,0.4241121,0.0007563613,0.00207503,0.003080305,0.1141818],"study_design_scores_gemma":[0.00002441887,0.0001229558,0.01342482,0.00002088027,0.00007618685,0.00004778134,0.0000592889,0.9835778,0.0003616279,0.001884537,0.0003797478,0.0000199519],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.775776,0.0005391097,0.2160732,0.001443812,0.0001662114,0.0004138594,0.002428124,0.001123448,0.002036211],"genre_scores_gemma":[0.9697813,0.00008012526,0.02811144,0.00007748068,0.00004999423,0.0001619594,0.001358575,0.00003388232,0.0003453002],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01073109,"threshold_uncertainty_score":0.05675209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.266526795618533,"score_gpt":0.3625100318712322,"score_spread":0.09598323625269922,"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."}}