{"id":"W4379054525","doi":"10.2196/48072","title":"Acquisition of a Lexicon for Family History Information: Bidirectional Encoder Representations From Transformers–Assisted Sublanguage Analysis","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Cancer Institute; National Institutes of Health","keywords":"Sublanguage; Encoder; Lexicon; Computer science; Natural language processing; Transformer; Artificial intelligence; Engineering; Electrical 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006046027,0.001121173,0.0005627533,0.002334759,0.0004829116,0.00148283,0.001191495,0.000632218,0.006125274],"category_scores_gemma":[0.004186649,0.0004747275,0.0009350183,0.001431718,0.0004361198,0.002037463,0.00180156,0.001100676,0.003873335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009677344,"about_ca_system_score_gemma":0.002825096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01257974,"about_ca_topic_score_gemma":0.01709252,"domain_scores_codex":[0.9994855,0.0001045261,0.00006680103,0.0001671553,0.0001216994,0.00005426551],"domain_scores_gemma":[0.9984142,0.0007994502,0.0001074676,0.0002105414,0.0004114173,0.00005685239],"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":[0.0003303851,0.0002494228,0.005819289,0.0005349134,0.0001349363,0.001502147,0.000746783,0.01679561,0.03406738,0.01317204,0.03557829,0.8910687],"study_design_scores_gemma":[0.0001091987,0.0001850037,0.004686856,0.0002028236,0.0003051442,0.001253264,0.0008143661,0.8661867,0.05184278,0.03173158,0.04257311,0.000109158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08680161,0.001003429,0.8665411,0.000857887,0.0002795588,0.000581326,0.01173353,0.02168599,0.0105156],"genre_scores_gemma":[0.4430108,0.0007858781,0.5156858,0.0003991364,0.0001022197,0.0005056864,0.03343648,0.0008026842,0.005271162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01257974,"threshold_uncertainty_score":0.02501303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588296098246193,"score_gpt":0.288193836415962,"score_spread":0.2723108754335,"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."}}