{"id":"W4406833305","doi":"10.2196/57275","title":"Large Language Model Approach for Zero-Shot Information Extraction and Clustering of Japanese Radiology Reports: Algorithm Development and Validation","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Radiology practices and education","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Information extraction; Artificial intelligence; Machine learning; Natural language processing; Data mining; Information retrieval","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002581344,0.00006050898,0.0001356948,0.00009525059,0.00005402308,0.000008900367,0.00001208603,0.00008561229,0.00000435092],"category_scores_gemma":[0.00004348656,0.00005428783,0.00001304535,0.00005587037,0.00001902401,0.0002861461,0.00001236529,0.00006126126,9.894839e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000681667,"about_ca_system_score_gemma":0.0001042912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004697141,"about_ca_topic_score_gemma":0.000003889892,"domain_scores_codex":[0.999513,0.00001228033,0.0002302331,0.0001106827,0.00004459016,0.00008923777],"domain_scores_gemma":[0.9996354,0.0000293501,0.0001640911,0.00008114375,0.00006525582,0.00002477906],"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":[0.001695348,0.0005652763,0.0284949,0.005603244,0.0006735412,0.000005694902,0.1867809,0.007795329,0.02857574,0.0003342851,0.008729547,0.7307463],"study_design_scores_gemma":[0.003334577,0.0001678391,0.04747964,0.000198116,0.0002899947,0.0004345738,0.02234297,0.9016554,0.00652442,0.0001043806,0.0171883,0.0002798311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7860164,0.0005930311,0.211369,0.0002584234,0.0001697535,0.0006507159,0.000006838678,0.00001699771,0.0009188578],"genre_scores_gemma":[0.9529107,0.000146704,0.04535031,0.0002323682,0.0000500325,0.0004232823,0.0002398825,0.000004798801,0.0006419781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.89386,"threshold_uncertainty_score":0.2213794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02792160276951978,"score_gpt":0.3638044400820019,"score_spread":0.3358828373124821,"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."}}