{"id":"W6902186868","doi":"10.6084/m9.figshare.16909630.v1","title":"Additional file 2 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; Health records; General practice; Quality (philosophy); Health data; Data collection; Quality assessment","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":[0.009209263,0.0001025405,0.0003452033,0.00004073869,0.0002239953,0.0001440564,0.001041858,0.0000651772,0.7335204],"category_scores_gemma":[0.1267979,0.00007679172,0.0001131804,0.0003595965,0.00002922866,0.001056325,0.0009792642,0.0002186467,0.00005791522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001214039,"about_ca_system_score_gemma":0.004459825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001307454,"about_ca_topic_score_gemma":0.000195294,"domain_scores_codex":[0.9947143,0.001445887,0.001675484,0.000650821,0.001252288,0.000261217],"domain_scores_gemma":[0.9609271,0.03368889,0.001846636,0.001953735,0.001490575,0.0000930967],"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":[0.00001364755,0.0002812188,0.00001476936,0.00008546634,0.0000424237,1.793086e-7,0.00004658763,0.00007344095,4.491812e-7,0.000311219,0.9536595,0.04547104],"study_design_scores_gemma":[0.0001693384,0.00004836174,0.01662548,0.0002286645,0.00000870385,0.000001272299,0.000568822,0.03538263,0.000006774457,0.001877711,0.9450108,0.00007143502],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00003398335,0.00005194485,0.005150465,0.001214917,0.00005790824,0.0003619709,0.9914119,0.00001314982,0.001703728],"genre_scores_gemma":[0.0007647444,0.000007436012,0.06440175,0.000737238,0.00008591441,0.0003716804,0.9326826,0.000006089073,0.0009425163],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7334625,"threshold_uncertainty_score":0.8805575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6515578119347073,"score_gpt":0.5949122324697573,"score_spread":0.05664557946494997,"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."}}