{"id":"W6977134819","doi":"10.6084/m9.figshare.16909645.v1","title":"Additional file 7 of Assessing the suitability of general practice electronic health records for clinical prediction model development: a data quality assessment","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Data quality; Record linkage; Quality (philosophy); Health records; General practice; Health data; Quality assessment; Data collection","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009264524,0.0001025815,0.0003452965,0.00004077053,0.0002240838,0.0001441276,0.001042252,0.00006517828,0.7264003],"category_scores_gemma":[0.1258592,0.00007681958,0.0001132115,0.0003598054,0.00002924047,0.00105669,0.000979195,0.0002186883,0.00005770208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001214279,"about_ca_system_score_gemma":0.004471221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001310097,"about_ca_topic_score_gemma":0.0001970096,"domain_scores_codex":[0.9947128,0.001445684,0.001676049,0.0006512269,0.001252852,0.0002613594],"domain_scores_gemma":[0.9608333,0.03379232,0.001841246,0.001951673,0.001488512,0.00009295499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001373984,0.0002816351,0.00001523584,0.00008631108,0.00004243997,1.775607e-7,0.00004668302,0.0000731952,4.637195e-7,0.0003146295,0.9538747,0.04525079],"study_design_scores_gemma":[0.0001697993,0.00004854574,0.01680132,0.0002338801,0.000008727698,0.000001271124,0.0005735886,0.03577161,0.000006901019,0.001886922,0.9444258,0.00007164802],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00003444429,0.00005158558,0.005310266,0.001220106,0.00005763588,0.0003628038,0.9912798,0.00001315649,0.00167025],"genre_scores_gemma":[0.0007941145,0.000007368343,0.06506292,0.0007380818,0.0000848708,0.0003715935,0.9320025,0.000006098703,0.0009324118],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7263426,"threshold_uncertainty_score":0.8815041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6550559088450293,"score_gpt":0.5950021434766101,"score_spread":0.06005376536841922,"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."}}