{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04422695,0.0006055607,0.0005598056,0.008527382,0.001434583,0.003130889,0.001771542,0.001084998,0.0008933864],"category_scores_gemma":[0.1735674,0.0004254739,0.002000741,0.009665099,0.001314015,0.003964981,0.00433308,0.001550092,0.0001710255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003573282,"about_ca_system_score_gemma":0.003962558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02020819,"about_ca_topic_score_gemma":0.0172992,"domain_scores_codex":[0.9724647,0.01350244,0.003984206,0.00288659,0.00643305,0.0007291064],"domain_scores_gemma":[0.8072685,0.1467118,0.0130882,0.01325689,0.01852925,0.001145355],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002759732,0.001983843,0.5219882,0.001753839,0.001303263,0.0007758453,0.008478712,0.06077001,0.008951177,0.02418413,0.006186342,0.360865],"study_design_scores_gemma":[0.0003302981,0.00076621,0.1923802,0.000559547,0.001108177,0.000546702,0.009241244,0.7425599,0.01580007,0.02247893,0.01399648,0.0002322254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7144868,0.0003621545,0.2727014,0.000846122,0.00007864189,0.001999012,0.005253619,0.001334771,0.002937589],"genre_scores_gemma":[0.7645732,0.0001368764,0.2248898,0.0001075001,0.00001590812,0.001570874,0.008320137,0.0001292977,0.0002563488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9557731,"threshold_uncertainty_score":0.2338973,"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."}}