{"id":"W3113186412","doi":"10.1186/s12911-020-01288-7","title":"Web-based interactive mapping from data dictionaries to ontologies, with an application to cancer registry","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health","keywords":"Computer science; Ontology; Interface (matter); Data dictionary; Information retrieval; Data mapping; User interface; Health informatics; Cancer registry; Data mining; Database; Cancer; Metadata; World Wide Web; Health care; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002342385,0.0001366983,0.0001888271,0.00004239254,0.00009949615,0.00007973621,0.0005151417,0.0001684439,0.00002975487],"category_scores_gemma":[0.001223225,0.00009926618,0.00001779117,0.0001520672,0.00009740931,0.00001714684,0.0005104369,0.0001393258,0.000007740797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001323892,"about_ca_system_score_gemma":0.0002925584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004694434,"about_ca_topic_score_gemma":0.0005508026,"domain_scores_codex":[0.9987453,0.00002587887,0.0003448456,0.0003104586,0.0004015848,0.000171907],"domain_scores_gemma":[0.9987165,0.0002605634,0.0001211316,0.0004674525,0.00006924724,0.0003650789],"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":[0.001013002,0.00003242422,0.005212455,0.00005142075,0.00003480346,0.000003916371,0.000615248,0.0008041392,0.0004971385,0.00002520746,0.009656217,0.9820541],"study_design_scores_gemma":[0.001468276,0.000750548,0.004953299,0.0006286619,0.0000284656,0.00001096238,0.004875156,0.7699413,0.0003608397,0.000163968,0.2163933,0.0004252192],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2899891,0.0001360958,0.7089973,0.0005091101,0.00005626802,0.0001209707,0.00008604574,0.0000313352,0.00007375495],"genre_scores_gemma":[0.5253757,0.0000422684,0.4666696,0.007442123,0.0001944358,0.00003672495,0.0002273936,0.000008897181,0.000002867428],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9816288,"threshold_uncertainty_score":0.4047957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05915755765944522,"score_gpt":0.3541183092545432,"score_spread":0.294960751595098,"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."}}