{"id":"W4323539565","doi":"10.21203/rs.3.rs-2640617/v1","title":"Cerebrovascular disease case identification in inpatient electronic medical record data using natural language processing","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Chart; Medical record; Medicine; Electronic medical record; Electronic health record; Coding (social sciences); Artificial intelligence; Predictive value; Clinical decision support system; Identification (biology); Medical diagnosis; Computer science; Natural language processing; Machine learning; Medical emergency; Statistics; Internal medicine; Decision support system; Pathology; Health care","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":[0.004832333,0.0004556396,0.0004442628,0.005155134,0.0003476993,0.001176185,0.0007564768,0.0004237322,0.000754753],"category_scores_gemma":[0.01972291,0.0001843597,0.0007406803,0.002579941,0.0003980212,0.0009262812,0.0007032881,0.0005286708,0.0002788821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001289353,"about_ca_system_score_gemma":0.001892722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01259759,"about_ca_topic_score_gemma":0.01623189,"domain_scores_codex":[0.9960318,0.001851877,0.0006513538,0.0007647177,0.0005725948,0.0001275924],"domain_scores_gemma":[0.9802325,0.01433781,0.002959299,0.000607995,0.001677719,0.000184659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005079486,0.0009142516,0.7105111,0.001628567,0.0003386766,0.001294331,0.001341831,0.02679131,0.004752742,0.001297899,0.008510668,0.2421106],"study_design_scores_gemma":[0.0001394006,0.0004324272,0.3603642,0.0006504366,0.0002833098,0.001119702,0.00197762,0.6151593,0.006247575,0.0065111,0.006999147,0.0001158634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.874867,0.001375398,0.09503268,0.002004697,0.0000798658,0.00189916,0.02103799,0.001216233,0.002486939],"genre_scores_gemma":[0.8433693,0.0003704898,0.139082,0.0003879402,0.0001008444,0.0008146117,0.01561417,0.0000197103,0.0002410278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01259759,"threshold_uncertainty_score":0.02555609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1224798412305595,"score_gpt":0.4628552906587924,"score_spread":0.3403754494282328,"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."}}