{"id":"W3045889620","doi":"10.2196/17376","title":"Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health","keywords":"Computer science; Information retrieval; Concept search; Unstructured data; Software portability; Scalability; Data mining; Database; Big data; Search engine; Web search query","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":[0.002853878,0.0001514693,0.0004632753,0.00001848098,0.00009507054,0.00002473773,0.001499728,0.0004235573,0.000005346104],"category_scores_gemma":[0.00215928,0.0001001235,0.00008546677,0.0001368322,0.0004498228,0.00003475195,0.0009147558,0.0002164338,2.43966e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002082614,"about_ca_system_score_gemma":0.0008724668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000159632,"about_ca_topic_score_gemma":0.000006753642,"domain_scores_codex":[0.9963629,0.0001775762,0.001799091,0.0002493536,0.001209582,0.0002014658],"domain_scores_gemma":[0.9974397,0.0003706448,0.0007938811,0.0009685321,0.0002088715,0.0002183358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003095064,0.0010232,0.6227338,0.02101243,0.005687384,0.00002575666,0.01375136,0.00134809,0.0009093066,0.010971,0.2103968,0.1090459],"study_design_scores_gemma":[0.001873662,0.0004610704,0.001149674,0.000324548,0.0002835551,0.00002940538,0.01194105,0.9702589,0.008369425,0.00001387166,0.005065347,0.0002294861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6420379,0.0002434512,0.351606,0.002898081,0.0005810743,0.001488491,0.001013551,0.0000681498,0.00006336724],"genre_scores_gemma":[0.9834931,0.0000174962,0.01073225,0.0004048611,0.0004716956,0.00002503,0.004837684,0.00001375707,0.000004084928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9689108,"threshold_uncertainty_score":0.4082918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3134486461483542,"score_gpt":0.4776412865090831,"score_spread":0.1641926403607289,"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."}}