{"id":"W4408905851","doi":"10.1016/j.semcancer.2025.03.004","title":"From classical approaches to artificial intelligence, old and new tools for PDAC risk stratification and prediction","year":2025,"lang":"en","type":"review","venue":"Seminars in Cancer Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pancreas Centre (Canada)","funders":"European Cooperation in Science and Technology; European Commission; Orta Doğu Teknik Üniversitesi; Cancer Research UK; Pancreatic Cancer UK","keywords":"Risk stratification; Stratification (seeds); Artificial intelligence; Computer science; Computational biology; Biology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003861174,0.0002322332,0.0009611193,0.0002206405,0.00005166686,0.00003907779,0.00009433767,0.0004241653,0.00001472121],"category_scores_gemma":[0.0008223266,0.0001861464,0.00008442275,0.0002113669,0.0001438315,0.00003181798,0.00005955098,0.0005978797,8.693159e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001256057,"about_ca_system_score_gemma":0.0003615076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003992924,"about_ca_topic_score_gemma":0.00008666779,"domain_scores_codex":[0.9984441,0.0001166079,0.0005255769,0.000634543,0.00006315629,0.0002160376],"domain_scores_gemma":[0.9985313,0.0009346077,0.0001671008,0.0001971363,0.00001764711,0.0001521891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005517761,0.00002545821,0.0002408233,0.001590091,0.00007000486,0.000001067407,0.0001917471,0.000004314727,0.000008201482,0.001573436,0.001035785,0.9952039],"study_design_scores_gemma":[0.0002360468,0.0003674515,0.0001502767,0.01354091,0.001001468,0.00001249682,0.0001518691,0.003466714,0.00001754709,0.01254574,0.9682493,0.000260206],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004274322,0.9741186,0.02106803,0.001871382,0.0005827632,0.001397813,0.0004092736,0.00002536927,0.00009933035],"genre_scores_gemma":[0.0001235829,0.9888833,0.008469952,0.0001390421,0.0009927024,0.0003879767,0.0006825253,0.00001933901,0.0003016256],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9949437,"threshold_uncertainty_score":0.7590832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.178276850204085,"score_gpt":0.4096658170760843,"score_spread":0.2313889668719993,"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."}}