{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008523177,0.000099052,0.0002225642,0.00006147831,0.0001270888,0.001077051,0.0006576719,0.00007115555,0.000005876373],"category_scores_gemma":[0.001679406,0.00005175926,0.00004517097,0.000349803,0.00006298575,0.00265357,0.0002735261,0.0005543267,0.00000599756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000110045,"about_ca_system_score_gemma":0.0001227633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002437825,"about_ca_topic_score_gemma":0.000003631927,"domain_scores_codex":[0.9979494,0.00009158192,0.0006346073,0.00005502913,0.001096706,0.0001726547],"domain_scores_gemma":[0.9976279,0.000658698,0.001140443,0.0001651855,0.0002207499,0.000187046],"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":[0.000003473974,0.00001222707,0.001403918,0.0000073216,0.00003654371,9.821401e-7,0.01666948,0.00003836698,0.00002977713,0.00002352253,0.004296987,0.9774774],"study_design_scores_gemma":[0.0004085018,0.0000601062,0.04296767,0.0002190723,0.00001880735,0.00002954585,0.002337737,0.9501871,0.00002389588,0.0007443142,0.002893948,0.0001093088],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7074151,0.0003703824,0.2700522,0.02152005,0.000422912,0.0001568288,0.00001279676,0.00001856719,0.00003121623],"genre_scores_gemma":[0.8729013,0.0000682542,0.1149446,0.01167861,0.0003757435,0.000003572561,0.00001218923,0.000004096026,0.00001157156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9773681,"threshold_uncertainty_score":0.9999599,"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."}}