{"id":"W3110873124","doi":"10.2196/24008","title":"Family History Extraction From Synthetic Clinical Narratives Using Natural Language Processing: Overview and Evaluation of a Challenge Data Set and Solutions for the 2019 National NLP Clinical Challenges (n2c2)/Open Health Natural Language Processing (OHNLP) Competition","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Natural language processing; Natural history; Computer science; Set (abstract data type); Narrative; Natural (archaeology); Artificial intelligence; Data set; Natural language; Data science; Medicine; Linguistics; History; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002187839,0.0001393911,0.0002799269,0.00002393244,0.0001760736,0.00004367047,0.0003343364,0.0001621446,0.000009653182],"category_scores_gemma":[0.0006450747,0.0001033214,0.00005857654,0.00003778948,0.0002792263,0.00007552625,0.0003897943,0.000255636,5.516762e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004084356,"about_ca_system_score_gemma":0.001115248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002555509,"about_ca_topic_score_gemma":0.00007191184,"domain_scores_codex":[0.9981454,0.0002324719,0.0007181506,0.0002581878,0.0004760592,0.0001697575],"domain_scores_gemma":[0.9987332,0.0001634366,0.0005007185,0.000209127,0.0002368527,0.0001567004],"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":[0.0004802645,0.0005277669,0.00009345897,0.001731192,0.0002970242,0.000002254099,0.0294437,0.00002956653,0.001178973,0.0003131343,0.006249678,0.959653],"study_design_scores_gemma":[0.00299502,0.000447703,0.007846878,0.0006069237,0.0001973871,0.00002541131,0.03857365,0.9311049,0.00001263959,0.0001204288,0.01771701,0.0003520579],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.580488,0.4106691,0.001479025,0.005013959,0.0003672923,0.001322239,0.0005370011,0.00001758977,0.0001058026],"genre_scores_gemma":[0.9881267,0.006796237,0.001694642,0.001441298,0.0004094366,0.00003074064,0.001483921,0.00001280674,0.000004209266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9593009,"threshold_uncertainty_score":0.4213323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2907145640907986,"score_gpt":0.4810624134638092,"score_spread":0.1903478493730106,"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."}}