{"id":"W4415473192","doi":"10.2196/78332","title":"Enabling Just-in-Time Clinical Oncology Analysis With Large Language Models: Feasibility and Validation Study Using Unstructured Synthetic Data","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Proof of concept; Clinical Oncology; Unstructured data; Synthetic data; Software; Patient data; Data format","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007167677,0.00096869,0.0004007411,0.001038224,0.0004133731,0.001320868,0.001505338,0.0009349114,0.001667651],"category_scores_gemma":[0.02851403,0.0002774918,0.0009533705,0.000796347,0.000694069,0.001422864,0.001775961,0.0009844069,0.0009031925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008939089,"about_ca_system_score_gemma":0.001564226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003569427,"about_ca_topic_score_gemma":0.004122138,"domain_scores_codex":[0.9957813,0.002676774,0.0003157137,0.000670629,0.0004189362,0.0001365948],"domain_scores_gemma":[0.9700059,0.02452272,0.000913433,0.002499433,0.00154323,0.000515349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004858639,0.004091281,0.1186955,0.003260079,0.0008467912,0.002894905,0.005520569,0.3172894,0.02944869,0.008384476,0.04737625,0.4573334],"study_design_scores_gemma":[0.0004260232,0.001300574,0.01819462,0.0001666877,0.0001193137,0.000785277,0.001656173,0.9322947,0.02155405,0.007044829,0.01636239,0.00009536608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8351164,0.0008164499,0.1345355,0.00192291,0.0002211012,0.001535693,0.01332221,0.00939988,0.003129829],"genre_scores_gemma":[0.7740561,0.0002367247,0.1996331,0.0004716729,0.00007289976,0.001049776,0.02325017,0.00021957,0.001010016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007167677,"threshold_uncertainty_score":0.03790677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1076523247402565,"score_gpt":0.4219480722279051,"score_spread":0.3142957474876487,"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."}}