{"id":"W6939816637","doi":"10.6084/m9.figshare.19759377","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":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","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":[0.001929791,0.0009376986,0.0007580727,0.003456906,0.0004828718,0.001345468,0.001379505,0.0008416084,0.6146495],"category_scores_gemma":[0.02253703,0.0004251018,0.0007531533,0.003304801,0.0002092407,0.001156508,0.001331048,0.0006540917,0.107034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009501237,"about_ca_system_score_gemma":0.002021685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003453317,"about_ca_topic_score_gemma":0.006333856,"domain_scores_codex":[0.9989042,0.0001867274,0.0003266291,0.0002962908,0.0002027421,0.00008327788],"domain_scores_gemma":[0.9779691,0.01585146,0.001667617,0.001194812,0.002894799,0.0004222346],"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":[0.0003851202,0.00009649856,0.003552163,0.003112231,0.00006322245,0.0001352505,0.00008398762,0.0004839204,0.0006525442,0.0006834225,0.9693597,0.02139184],"study_design_scores_gemma":[0.002292588,0.0003106616,0.03757791,0.001973472,0.0002312558,0.0007534393,0.0004363363,0.005229626,0.005346882,0.008259447,0.9374108,0.0001775743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002913724,0.00001784805,0.0008466406,0.00008616795,0.00001844407,0.00009613857,0.9969897,0.001052674,0.0006009045],"genre_scores_gemma":[0.006510316,0.00008495095,0.009502603,0.0002798326,0.00009032284,0.001417965,0.977553,0.0008323705,0.003728645],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.6146495,"threshold_uncertainty_score":0.5496557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06159696220275089,"score_gpt":0.3468738021064304,"score_spread":0.2852768399036795,"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."}}