{"id":"W6977333029","doi":"10.6084/m9.figshare.16909642.v1","title":"Additional file 6 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":"Medical Coding and Health Information","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Data quality; Coding (social sciences); General practice; Health records; Health data; Data collection; Quality (philosophy); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004395757,0.00009400056,0.0003274898,0.00002688306,0.0006794928,0.000009906577,0.0002673333,0.000178803,0.6832774],"category_scores_gemma":[0.06612427,0.00007436344,0.00006181261,0.0001642024,0.00001657644,0.0004364577,0.0002474455,0.0007883034,0.00004447416],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003209511,"about_ca_system_score_gemma":0.02155006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002427611,"about_ca_topic_score_gemma":0.0001191818,"domain_scores_codex":[0.9955444,0.001420123,0.001870702,0.000277025,0.000489387,0.0003983758],"domain_scores_gemma":[0.9742084,0.02184809,0.001847617,0.0006727455,0.001274564,0.0001486291],"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":[0.00002177727,0.0001142581,0.00008915846,0.001719613,0.0000216729,5.044735e-8,0.0002474786,0.00001646358,2.213596e-7,0.000114066,0.9856762,0.01197902],"study_design_scores_gemma":[0.0003312012,0.00006106186,0.02774954,0.002199524,0.000007609471,8.208009e-7,0.0006242593,0.07427131,0.00000126895,0.0001487287,0.8945453,0.00005939667],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0000776688,0.00006177159,0.001597139,0.001894038,0.0001037289,0.000721453,0.9928882,0.00003069119,0.002625315],"genre_scores_gemma":[0.001052922,0.00002062359,0.0385634,0.002162174,0.0002692615,0.001336087,0.9561467,0.000009761678,0.0004391085],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.6832329,"threshold_uncertainty_score":0.9839968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7108694782500007,"score_gpt":0.6277856902109716,"score_spread":0.08308378803902905,"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."}}