{"id":"W4386387286","doi":"10.1186/s40708-023-00203-w","title":"Cerebrovascular disease case identification in inpatient electronic medical record data using natural language processing","year":2023,"lang":"en","type":"article","venue":"Brain Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Identification (biology); Electronic medical record; Medicine; Medical record; Disease; Computer science; Natural language processing; Medical emergency; Pathology; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001856079,0.0001293074,0.0001432476,0.0003127806,0.0001693966,0.0002097953,0.001245147,0.00006861558,0.000009017604],"category_scores_gemma":[0.002041886,0.0001251112,0.00003035649,0.001223629,0.00003107935,0.001353618,0.0008694975,0.000514258,0.00004838868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001728001,"about_ca_system_score_gemma":0.0006412266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003041433,"about_ca_topic_score_gemma":0.0002823874,"domain_scores_codex":[0.997797,0.0001532906,0.0006724908,0.0002323958,0.0006833997,0.0004614457],"domain_scores_gemma":[0.998239,0.0001765685,0.0002316453,0.001119672,0.00006191729,0.0001712257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001238534,0.0000714481,0.01579443,0.001990135,0.00002299324,0.001369158,0.03213541,0.007305537,0.00001049745,0.001711995,0.001930995,0.937645],"study_design_scores_gemma":[0.0002164701,0.00001061951,0.002496658,0.000132162,0.000003827279,0.0002529886,0.0006635207,0.9950455,0.000002528966,0.000115591,0.0009158909,0.0001442584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8970298,0.0003303254,0.09897058,0.002283565,0.0005095895,0.0004172859,0.0000106466,0.0004136576,0.00003461102],"genre_scores_gemma":[0.9913995,0.00001530611,0.007511297,0.0007329083,0.00006275441,0.000008720722,0.000213215,0.0000134558,0.00004282265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9877399,"threshold_uncertainty_score":0.5101887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02924179200630377,"score_gpt":0.3474506794720171,"score_spread":0.3182088874657134,"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."}}