{"id":"W1838551284","doi":"10.1136/amiajnl-2013-002214","title":"Natural language processing: algorithms and tools to extract computable information from EHRs and from the biomedical literature","year":2013,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"CONTEST; Computer science; Narrative; Natural language processing; Health records; Artificial intelligence; Task (project management); Interpretation (philosophy); Structuring; Information retrieval; Biomedical text mining; Quality (philosophy); Text mining; Linguistics; Programming language; Health care","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009997256,0.002528386,0.001969578,0.01574003,0.001363102,0.006620079,0.00295542,0.001923036,0.004546032],"category_scores_gemma":[0.02826357,0.000962064,0.003168588,0.01242681,0.002028424,0.008150849,0.003679759,0.003081443,0.004501986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001681918,"about_ca_system_score_gemma":0.003844746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003961409,"about_ca_topic_score_gemma":0.004513519,"domain_scores_codex":[0.9931542,0.002841451,0.001171477,0.001002677,0.001709677,0.0001204568],"domain_scores_gemma":[0.9807818,0.01563314,0.0009576302,0.001125476,0.001337596,0.0001644095],"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":[0.0001160535,0.0002215493,0.00209395,0.004864482,0.0003876763,0.000395029,0.001068562,0.009240581,0.005338544,0.04299458,0.04104234,0.8922366],"study_design_scores_gemma":[0.0001354199,0.0001813278,0.00429578,0.002665428,0.0004011914,0.0011609,0.00169514,0.2433478,0.01367432,0.5127686,0.2193838,0.0002903926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002969557,0.007898379,0.9711182,0.002662401,0.0003081642,0.0006808842,0.005512356,0.005968153,0.002881997],"genre_scores_gemma":[0.01469819,0.006084793,0.9666205,0.0004917975,0.0003893248,0.001023148,0.009229584,0.0003368515,0.001125885],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01574003,"threshold_uncertainty_score":0.05287123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005966570501120155,"score_gpt":0.2444841220209323,"score_spread":0.2385175515198122,"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."}}