{"id":"W6902057674","doi":"10.6084/m9.figshare.19759383.v1","title":"Additional file 3 of Automated medical chart review for breast cancer outcomes research: a novel natural language processing extraction system","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Prevention of Organ Failure; University of British Columbia","funders":"","keywords":"Breast cancer; Chart; Data extraction; Natural language; Gold standard (test)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001610309,0.001080369,0.0007746469,0.003381597,0.0005663586,0.001517772,0.001476578,0.0009171269,0.6729432],"category_scores_gemma":[0.01846326,0.0004534725,0.0009083546,0.003553593,0.0002536135,0.001350064,0.001313271,0.0007326297,0.1180505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00106151,"about_ca_system_score_gemma":0.002031229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004108138,"about_ca_topic_score_gemma":0.006521122,"domain_scores_codex":[0.9990785,0.0001341077,0.0002400349,0.0002408772,0.000222035,0.00008444794],"domain_scores_gemma":[0.9829403,0.01183656,0.001249623,0.0009770559,0.002608113,0.0003883859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003895027,0.00009205604,0.002879417,0.002437359,0.00006351767,0.0001493647,0.00008014758,0.0004957806,0.0006357487,0.0007495153,0.9740831,0.01794457],"study_design_scores_gemma":[0.002199735,0.0002065897,0.02405914,0.001474265,0.0002148244,0.0006975809,0.0003627542,0.004548653,0.005924333,0.008897787,0.9512491,0.0001652563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.0002848359,0.00001434353,0.0009517929,0.0001085545,0.00002319633,0.00009266124,0.9961677,0.001492921,0.0008639214],"genre_scores_gemma":[0.006197491,0.00007758856,0.009313242,0.0003199919,0.00009056983,0.001156355,0.9763431,0.001362087,0.005139627],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6729432,"threshold_uncertainty_score":0.4665068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06651094892406054,"score_gpt":0.4052983664027775,"score_spread":0.338787417478717,"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."}}