{"id":"W4392656250","doi":"10.1186/s12874-024-02192-8","title":"Text analysis framework for identifying mutations among non-small cell lung cancer patients from laboratory data","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Lexical analysis; Natural language processing; Artificial intelligence; Information extraction; Syntax; Context (archaeology); Population; Information retrieval; Medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002996126,0.001436573,0.0009026892,0.0102924,0.001028592,0.002403996,0.00191012,0.001075761,0.003006772],"category_scores_gemma":[0.009619177,0.0002949824,0.002209325,0.003952709,0.0005843586,0.002430291,0.001397169,0.001153561,0.001692688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001393517,"about_ca_system_score_gemma":0.002967417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01103615,"about_ca_topic_score_gemma":0.01581187,"domain_scores_codex":[0.9975954,0.0004057424,0.0004965479,0.000749804,0.0006220591,0.0001305097],"domain_scores_gemma":[0.9949267,0.002838059,0.0005623327,0.0002339894,0.001201319,0.0002375519],"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":[0.0007287283,0.0007058026,0.02897797,0.003376939,0.0005045165,0.005378133,0.00214581,0.03805304,0.02694929,0.02967497,0.05940557,0.8040993],"study_design_scores_gemma":[0.0001691001,0.0003593407,0.01799064,0.0007717803,0.0006555614,0.002618612,0.00168691,0.7923891,0.02326487,0.07334875,0.08656633,0.0001790125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02704701,0.00178959,0.9085647,0.002688992,0.0002198853,0.002493042,0.03506503,0.01808542,0.004046368],"genre_scores_gemma":[0.1196953,0.0007308894,0.8195779,0.000576472,0.0001757861,0.001216059,0.05560492,0.0002506442,0.002171939],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01103615,"threshold_uncertainty_score":0.02194387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.354800330344782,"score_gpt":0.5470634171707748,"score_spread":0.1922630868259927,"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."}}