{"id":"W2790121460","doi":"10.2196/medinform.8175","title":"Representation of Time-Relevant Common Data Elements in the Cancer Data Standards Repository: Statistical Evaluation of an Ontological Approach","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Cancer Institute","keywords":"Computer science; Data science; Data sharing; Data quality; Dimension (graph theory); Representation (politics); Domain (mathematical analysis); Data integration; Data mining; Service (business); Medicine; Pathology","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":[0.004379008,0.0000963466,0.0002364011,0.00003185801,0.00004281117,0.00001493087,0.001417757,0.0002212685,0.00007171469],"category_scores_gemma":[0.001665473,0.00006018681,0.00001646456,0.0001481095,0.0006797791,0.00002174414,0.0005720123,0.0001567352,0.000001031522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002021035,"about_ca_system_score_gemma":0.000413502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001283391,"about_ca_topic_score_gemma":0.0001484883,"domain_scores_codex":[0.9968485,0.0004071706,0.000769925,0.0002131812,0.001593455,0.0001677442],"domain_scores_gemma":[0.9979524,0.00009014606,0.0002850295,0.00136328,0.0002316179,0.00007753369],"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":[0.0008542115,0.001809861,0.0182594,0.000413258,0.000283834,0.000007765202,0.005454058,0.00002661772,0.003727281,0.0002570022,0.08218405,0.8867227],"study_design_scores_gemma":[0.003426147,0.00197908,0.03052303,0.0001851908,0.0002218011,0.00005399946,0.006676747,0.9379203,0.004596228,0.0003212373,0.01378024,0.0003159817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883204,0.0001649777,0.007830535,0.0001547985,0.000106869,0.0004490598,0.0009186976,0.000009543071,0.002045131],"genre_scores_gemma":[0.9817823,0.00006420889,0.01333223,0.0001723058,0.0001612481,0.00003368306,0.004442114,0.000005410109,0.000006542101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9378937,"threshold_uncertainty_score":0.2634569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1058000960753875,"score_gpt":0.4493720295632368,"score_spread":0.3435719334878493,"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."}}