{"id":"W4406865074","doi":"10.2196/65984","title":"Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review","year":2025,"lang":"en","type":"review","venue":"JMIR Cancer","topic":"Topic Modeling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency; University of Waterloo; University of Toronto","funders":"","keywords":"Preprint; Computer science; Data science; Medicine; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0005794535,0.000171287,0.0008392148,0.0002229031,0.00007870112,0.00004282436,0.0004819349,0.0001512573,0.000005583608],"category_scores_gemma":[0.00002829442,0.0001611663,0.0001550482,0.0004786805,0.000004816461,0.0005260002,0.0001156347,0.0002531735,0.00001040285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008676596,"about_ca_system_score_gemma":0.003334893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003031761,"about_ca_topic_score_gemma":0.0002331222,"domain_scores_codex":[0.9984778,0.00007170512,0.0007653396,0.0002979788,0.000126277,0.0002608679],"domain_scores_gemma":[0.9987483,0.0001126034,0.0005310783,0.0005048561,0.00005724604,0.00004588616],"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":[2.224244e-7,0.0000115433,4.087238e-8,0.1647135,0.000003626922,7.769213e-8,0.0001395932,0.0001278574,6.019732e-9,0.00173851,0.001001111,0.8322639],"study_design_scores_gemma":[0.00009463304,0.000005953691,4.90376e-8,0.2031028,0.00001828248,0.000001258743,0.000004558371,0.02705512,3.345322e-8,0.00005948146,0.7695446,0.0001131677],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.735155e-9,0.516346,0.4791009,0.0004165104,0.00008576694,0.003797628,0.00003176437,0.00004293423,0.0001785886],"genre_scores_gemma":[1.082699e-7,0.9528505,0.02285774,0.002299844,0.00007616174,0.02167308,0.00009083879,0.000007113561,0.0001445722],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8321508,"threshold_uncertainty_score":0.657217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.074606718448783,"score_gpt":0.5065021944205048,"score_spread":0.4318954759717218,"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."}}