{"id":"W3109501393","doi":"10.2196/21750","title":"Family History Information Extraction With Neural Attention and an Enhanced Relation-Side Scheme: Algorithm Development and Validation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and Technology, Taiwan","keywords":"Computer science; Artificial neural network; Artificial intelligence; Relationship extraction; Information extraction; Machine learning; Scheme (mathematics); Task (project management); Inference; Relation (database); Sentence; Algorithm; Data mining","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":[0.0002412946,0.0001088791,0.0001088737,0.00007423621,0.00009021838,0.0001039967,0.0001456493,0.0001021267,0.000005724114],"category_scores_gemma":[0.00004133331,0.00009524724,0.00000974452,0.0001108836,0.00004110012,0.004805647,0.00008360892,0.0002130837,0.0000117183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009052838,"about_ca_system_score_gemma":0.0001515385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000446524,"about_ca_topic_score_gemma":0.000001070943,"domain_scores_codex":[0.9986659,0.00002436237,0.0004859483,0.0001042922,0.000586449,0.0001330698],"domain_scores_gemma":[0.9992991,0.00002738939,0.0002137707,0.0001310354,0.00008887488,0.0002398097],"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":[0.00001018415,0.00001761047,0.0002236801,0.0001242975,0.00001041701,0.000001558248,0.0254096,0.0001210968,0.0002003856,0.001846022,0.0001353318,0.9718998],"study_design_scores_gemma":[0.0005200096,0.00008171152,0.005567802,0.00003923718,0.000003717435,0.00001655852,0.0007321115,0.9883285,0.0002275971,0.00003561797,0.004305426,0.0001416876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3443973,0.00001635783,0.6546859,0.0002877953,0.00007541975,0.000143789,2.458358e-7,0.00009374507,0.0002994448],"genre_scores_gemma":[0.4596904,0.00001974903,0.5383302,0.001789893,0.00006664871,0.0000343384,0.0000542045,0.000004971319,0.000009584428],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9882074,"threshold_uncertainty_score":0.388407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02611977797276242,"score_gpt":0.2653891485497481,"score_spread":0.2392693705769857,"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."}}