{"id":"W3109225475","doi":"10.2196/22982","title":"Extracting Family History of Patients From Clinical Narratives: Exploring an End-to-End Solution With Deep Learning Models","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Chronic Disease Prevention and Health Promotion; Clinical and Translational Science Institute, University of Florida; National Center for Advancing Translational Sciences; University of Florida; National Cancer Institute; National Institutes of Health; Nvidia; Centers for Disease Control and Prevention; National Institute on Aging; Patient-Centered Outcomes Research Institute","keywords":"Computer science; Artificial intelligence; Conditional random field; Named-entity recognition; Machine learning; Relationship extraction; Deep learning; End-to-end principle; Natural language processing; Information extraction; Transformer; F1 score; Task (project management); Engineering","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":[0.0008179015,0.0001976311,0.0004014392,0.00009511906,0.000111139,0.00004073726,0.0008864415,0.0001726226,0.00005281776],"category_scores_gemma":[0.0007342437,0.0001706321,0.00006532637,0.000268246,0.000119862,0.002103275,0.0003714301,0.001358264,0.00002351388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001871194,"about_ca_system_score_gemma":0.0004428803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009882121,"about_ca_topic_score_gemma":0.00001468929,"domain_scores_codex":[0.9963514,0.0003491806,0.001240784,0.0002745829,0.001425793,0.0003583262],"domain_scores_gemma":[0.9975013,0.0004536302,0.0006103722,0.0003724648,0.0002249054,0.0008373913],"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":[0.000111906,0.0002023187,0.02531675,0.0002881342,0.0000421241,0.00001279166,0.4775273,0.01053134,0.00001061304,0.001047701,0.0004733196,0.4844357],"study_design_scores_gemma":[0.0006027237,0.0009709003,0.009292876,0.0001765964,0.000004901423,0.000001127435,0.006831276,0.9757607,0.000003168348,0.00006678974,0.006077962,0.0002109801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.500396,0.00003561753,0.4977026,0.0004394689,0.0003061468,0.000211511,0.000001738938,0.0001709968,0.0007359422],"genre_scores_gemma":[0.8657483,0.00001659537,0.13185,0.0021097,0.0001763993,0.00004151697,0.00003213951,0.00001708597,0.000008246526],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9652293,"threshold_uncertainty_score":0.6958176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1443492699324689,"score_gpt":0.3420522849313613,"score_spread":0.1977030149988923,"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."}}