{"id":"W6920873072","doi":"10.6084/m9.figshare.19759377.v1","title":"Additional file 1 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); Medical record","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":[0.001682388,0.0009833763,0.0007262373,0.003235851,0.0005217405,0.001378823,0.001458473,0.0008273894,0.6584403],"category_scores_gemma":[0.02038266,0.0004426881,0.0007703662,0.003648194,0.0002325513,0.00132269,0.001270452,0.0007357723,0.1198749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009855683,"about_ca_system_score_gemma":0.001988241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003376768,"about_ca_topic_score_gemma":0.005563368,"domain_scores_codex":[0.9991085,0.0001409338,0.0002267804,0.0002438569,0.0002036902,0.00007623959],"domain_scores_gemma":[0.9812024,0.01348715,0.001281891,0.001036635,0.002582925,0.0004091562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000338289,0.00009682073,0.002623297,0.002213672,0.00005458927,0.0001180914,0.00007055125,0.000464638,0.0005834695,0.0007005117,0.9730905,0.0196456],"study_design_scores_gemma":[0.002169057,0.0002459765,0.02630324,0.001387001,0.0002154451,0.0007504713,0.0003424425,0.004969887,0.005920783,0.008623487,0.9489114,0.0001608344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000271536,0.00001443619,0.0009631304,0.0001028516,0.00002064832,0.00008745561,0.9966063,0.0012206,0.0007130035],"genre_scores_gemma":[0.006185418,0.00008205972,0.01041522,0.0002952115,0.00009153,0.001179169,0.9762695,0.00112502,0.004356933],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.6584403,"threshold_uncertainty_score":0.4871935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06772187932270748,"score_gpt":0.4058671939093982,"score_spread":0.3381453145866907,"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."}}