{"id":"W6977275162","doi":"10.6084/m9.figshare.16909627","title":"Additional file 1 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":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Data quality; Coding (social sciences); Health records; Health data; General practice; Quality (philosophy); Data collection; Electronic health record","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00672426,0.0007862385,0.0009266391,0.002910395,0.0008696996,0.001528971,0.00158671,0.00114471,0.816663],"category_scores_gemma":[0.1308687,0.0004807491,0.001010327,0.004475464,0.0003099231,0.001668624,0.001215747,0.0009727779,0.07699957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001513679,"about_ca_system_score_gemma":0.003192322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005770491,"about_ca_topic_score_gemma":0.00900926,"domain_scores_codex":[0.9966828,0.001007851,0.001006602,0.0004534612,0.0006552392,0.0001939519],"domain_scores_gemma":[0.8232584,0.1483854,0.008033214,0.005685607,0.01346919,0.001168114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0006726861,0.0001807783,0.004967805,0.003899082,0.0001018671,0.00005752228,0.0001187849,0.0004653885,0.00006880381,0.001004079,0.9733256,0.01513754],"study_design_scores_gemma":[0.01683905,0.001162262,0.1125487,0.01352493,0.0008632813,0.001021669,0.001541987,0.006147698,0.001770211,0.01815348,0.8260736,0.0003529257],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0006073525,0.00001573077,0.0005580725,0.0001974124,0.00002364776,0.0004816553,0.9969002,0.0001535912,0.001062339],"genre_scores_gemma":[0.02757054,0.0001788936,0.01294278,0.001216674,0.0002114846,0.01706104,0.9273545,0.0008477177,0.01261642],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.816663,"threshold_uncertainty_score":0.2615079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3020492965549068,"score_gpt":0.5126365692006355,"score_spread":0.2105872726457287,"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."}}