{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003641439,0.0009200747,0.0004951101,0.003594197,0.0005376837,0.001004147,0.001127477,0.0008056854,0.001282301],"category_scores_gemma":[0.01219177,0.000302784,0.001000842,0.001745215,0.0003955083,0.001610449,0.00103228,0.001085129,0.001158184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007956984,"about_ca_system_score_gemma":0.001693128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00584685,"about_ca_topic_score_gemma":0.008778275,"domain_scores_codex":[0.9974915,0.000967213,0.0003513407,0.0006328694,0.0004649698,0.00009216509],"domain_scores_gemma":[0.9861572,0.01094946,0.0008618502,0.000651732,0.001250237,0.0001296038],"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":[0.0004591757,0.0005161692,0.03885076,0.001889771,0.0002536753,0.002303447,0.001667585,0.02406164,0.05403455,0.001783113,0.02460551,0.8495746],"study_design_scores_gemma":[0.0001556348,0.0004984866,0.08885871,0.0006933829,0.0005750178,0.003669642,0.003070746,0.7044625,0.1185675,0.02137363,0.05783081,0.0002440192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2335453,0.00383971,0.7236038,0.00446973,0.0002871405,0.00116219,0.01954344,0.01041401,0.003134494],"genre_scores_gemma":[0.3103254,0.001384244,0.6552504,0.0006944468,0.0002185003,0.0004974215,0.03002754,0.0001633389,0.001438621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00584685,"threshold_uncertainty_score":0.01925802,"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."}}