{"id":"W2986924890","doi":"10.1186/s12911-019-0970-1","title":"EXTraction of EMR numerical data: an efficient and generalizable tool to EXTEND clinical research","year":2019,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Gold standard (test); Vital signs; Glycated hemoglobin; Data extraction; Health informatics; Artificial intelligence; Data mining; Positive predicative value; Algorithm; Machine learning; Predictive value; Medicine; MEDLINE; Internal medicine; Surgery","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":[],"consensus_categories":[],"category_scores_codex":[0.02767324,0.00232178,0.001620668,0.01004946,0.000790593,0.005031986,0.002516139,0.001633139,0.006998051],"category_scores_gemma":[0.1365246,0.00115906,0.002583998,0.005460494,0.001027479,0.004597157,0.007253504,0.00187522,0.005570641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001049344,"about_ca_system_score_gemma":0.00343666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001669279,"about_ca_topic_score_gemma":0.002128809,"domain_scores_codex":[0.9753583,0.008381561,0.006855921,0.004405302,0.004623631,0.0003751724],"domain_scores_gemma":[0.8649833,0.09127916,0.01000408,0.01938181,0.01338513,0.0009664518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009956622,0.0004552007,0.02449263,0.006895646,0.0006445467,0.001732959,0.004276748,0.009334609,0.02205113,0.007705024,0.05343171,0.8679842],"study_design_scores_gemma":[0.001236908,0.001321873,0.07239684,0.007152791,0.001206643,0.005905523,0.003629045,0.3628582,0.1030447,0.08889161,0.3513613,0.0009945229],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01610135,0.000744349,0.867131,0.001380817,0.0001847363,0.003565679,0.02068879,0.08719035,0.003012859],"genre_scores_gemma":[0.03472016,0.0002866439,0.9469262,0.0004113886,0.00008700501,0.00201451,0.013201,0.001570042,0.0007831199],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02767324,"threshold_uncertainty_score":0.1463519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2018331812545356,"score_gpt":0.5280910745537604,"score_spread":0.3262578932992247,"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."}}