{"id":"W4413288733","doi":"10.1038/s41746-025-01941-3","title":"Incorporating large language models as clinical decision support in oncology: the Woollie model","year":2025,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Clinical decision making; Medicine; Oncology; Internal medicine; Computer science; Medical physics; Intensive care 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":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.004574677,0.0005948678,0.001962242,0.000468613,0.0001385884,0.00008823471,0.0007282178,0.001385838,0.0001126026],"category_scores_gemma":[0.03270349,0.0003674819,0.0003177295,0.0005688851,0.0005937787,0.0002571681,0.0004972302,0.005813658,0.00006210693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004138802,"about_ca_system_score_gemma":0.003025525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001183904,"about_ca_topic_score_gemma":0.00004497472,"domain_scores_codex":[0.9942886,0.000163546,0.001969011,0.0009812679,0.0018678,0.0007298351],"domain_scores_gemma":[0.9915897,0.006012877,0.0006176636,0.001002055,0.0002986262,0.000479116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004488138,0.0003118224,0.0002432439,0.0001534067,0.00009670187,0.0009523596,0.0006579154,0.0003226245,0.000005042633,0.0004328236,0.83469,0.1616853],"study_design_scores_gemma":[0.007795574,0.001218218,0.00003127339,0.003191793,0.0003236881,0.0000543912,0.0007806669,0.1767092,9.036036e-7,0.00959631,0.7999312,0.0003667042],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.005139059,0.002164917,0.02405055,0.01850288,0.6138919,0.001844633,0.0002735108,0.0003369686,0.3337956],"genre_scores_gemma":[0.1472938,0.001730962,0.003522618,0.01043429,0.8044274,0.0001399742,0.00434614,0.0002552222,0.02784958],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.305946,"threshold_uncertainty_score":0.9999106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01981051197987185,"score_gpt":0.4024374962192621,"score_spread":0.3826269842393902,"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."}}