{"id":"W3135857378","doi":"10.2196/24020","title":"Extracting Family History Information From Electronic Health Records: Natural Language Processing Analysis","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Commonwealth Scientific and Industrial Research Organisation","keywords":"Natural history; Health records; Text messaging; Family history; Computer science; Natural language processing; Medicine; Data science; World Wide Web; Health care","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":[0.0006456243,0.0001434855,0.0003012275,0.0002104358,0.0001095508,0.0001681727,0.0006006287,0.000122535,0.00007847233],"category_scores_gemma":[0.000211804,0.000133708,0.0001090759,0.0006864446,0.00002698503,0.002658791,0.0002195693,0.0006864233,0.00003909306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006540648,"about_ca_system_score_gemma":0.001919518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001920226,"about_ca_topic_score_gemma":0.0001100722,"domain_scores_codex":[0.997475,0.00006983676,0.0009113159,0.0001352082,0.0009585688,0.0004500924],"domain_scores_gemma":[0.9986165,0.0001044131,0.0004578794,0.0004655008,0.0001347629,0.0002209289],"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":[0.000002129691,0.00002471795,0.0001087345,0.0001017619,0.00006871035,0.000007762986,0.03961123,0.00009207616,0.000008950765,0.0007026465,0.0016623,0.957609],"study_design_scores_gemma":[0.0002443168,0.00001492894,0.0004912706,0.00007804141,0.00001915874,0.00001274841,0.004600025,0.9675293,0.00001835677,0.00009040135,0.02673952,0.0001619136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07167177,0.003638895,0.9209799,0.0009552822,0.0004585625,0.0001209858,0.000002434331,0.0002676906,0.001904497],"genre_scores_gemma":[0.8606693,0.000129322,0.1259267,0.01272429,0.0001843386,0.00002474937,0.0001965546,0.000008117202,0.0001365999],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9674373,"threshold_uncertainty_score":0.5452455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01431631597203063,"score_gpt":0.2881194847011004,"score_spread":0.2738031687290697,"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."}}