{"id":"W4404518252","doi":"10.1200/cci.24.00110","title":"Classifying Tumor Reportability Status From Unstructured Electronic Pathology Reports Using Language Models in a Population-Based Cancer Registry Setting","year":2024,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Provincial Health Services Authority; University of British Columbia","funders":"","keywords":"Medical diagnosis; Artificial intelligence; Population; Computer science; Cancer registry; Pipeline (software); Natural language processing; Machine learning; Cancer; Set (abstract data type); Medicine; Medical physics; Pathology; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00170761,0.0002874929,0.000538595,0.0001859766,0.0001207356,0.0002755343,0.0003852391,0.0002877151,0.0000429896],"category_scores_gemma":[0.0005070664,0.0002753714,0.00019522,0.0008095597,0.00008915973,0.001228101,0.0001836196,0.001181098,0.000001754433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002025738,"about_ca_system_score_gemma":0.00292847,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009180221,"about_ca_topic_score_gemma":0.004396013,"domain_scores_codex":[0.9952434,0.000188989,0.00264822,0.0006422383,0.0005440323,0.000733159],"domain_scores_gemma":[0.9968477,0.0005797836,0.001168282,0.001119459,0.0001254774,0.000159224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007356136,0.00005450435,0.5273212,0.0006099904,0.00008699128,0.0006175245,0.004266534,0.321431,0.0001368562,0.0004982693,0.0001738663,0.1447297],"study_design_scores_gemma":[0.000313558,0.00003834927,0.0272768,0.000347006,0.00003955622,0.00005639299,0.0001445032,0.9617425,0.0001653245,0.009055715,0.0004915257,0.0003287907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7769253,0.00164376,0.2177377,0.0002289187,0.002621018,0.0003601314,0.00005376268,0.0003356296,0.0000938385],"genre_scores_gemma":[0.9643356,0.0001051358,0.03418767,0.0008412914,0.0003558944,0.00009917159,0.00003805187,0.00002948392,0.000007757158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6403115,"threshold_uncertainty_score":0.9999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04502848308434197,"score_gpt":0.3846905372981353,"score_spread":0.3396620542137934,"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."}}