{"id":"W4402201868","doi":"10.3389/fdgth.2024.1427845","title":"A machine learning approach towards assessing consistency and reproducibility: an application to graft survival across three kidney transplantation eras","year":2024,"lang":"en","type":"article","venue":"Frontiers in Digital Health","topic":"Renal Transplantation Outcomes and Treatments","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"Wellcome Trust","keywords":"Receiver operating characteristic; Reproducibility; Consistency (knowledge bases); Mycophenolic acid; Transplantation; Machine learning; Medicine; Computer science; Tacrolimus; Artificial intelligence; Statistics; Internal medicine; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0007207576,0.0001767607,0.0003693131,0.0001471613,0.0001283371,0.0002196769,0.00005118707,0.0000629819,0.000001390616],"category_scores_gemma":[0.0000700958,0.0001505218,0.00005437609,0.0003632546,0.0000527861,0.0005127553,0.00001123032,0.0002290592,0.000002916723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000180026,"about_ca_system_score_gemma":0.0002570421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004599761,"about_ca_topic_score_gemma":0.00007728575,"domain_scores_codex":[0.9981218,0.00004708779,0.0003996083,0.0008777725,0.0002547079,0.0002990452],"domain_scores_gemma":[0.999194,0.00002812923,0.0000502018,0.0003285147,0.00003761185,0.0003615966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002614949,0.0002127688,0.6468429,0.00260444,0.00006300569,0.00004481447,0.003169889,0.00007905512,0.00001627721,0.0002129136,0.00002665252,0.3464658],"study_design_scores_gemma":[0.003953194,0.00118279,0.9409785,0.001708939,0.0001283582,0.000413998,0.001925172,0.04385872,0.00009145943,0.002538909,0.002711823,0.0005081712],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6126906,0.00284485,0.376038,0.002447933,0.0007716965,0.001870692,0.0004653921,0.0002958316,0.002575003],"genre_scores_gemma":[0.9862461,0.0003121359,0.01131872,0.0002950358,0.00005364399,0.00005362223,0.001485858,0.00003005727,0.0002048139],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3735556,"threshold_uncertainty_score":0.6138099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03236698903724294,"score_gpt":0.3519306700678004,"score_spread":0.3195636810305574,"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."}}