{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06231679,0.001341971,0.001216678,0.005234477,0.001083727,0.00278694,0.001701055,0.001646162,0.0006051784],"category_scores_gemma":[0.1239681,0.0003369353,0.002930402,0.003763241,0.001435951,0.001753065,0.002697401,0.003007893,0.000168724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001551335,"about_ca_system_score_gemma":0.001914361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004776981,"about_ca_topic_score_gemma":0.003055593,"domain_scores_codex":[0.9777166,0.01506591,0.001660849,0.002617816,0.002521689,0.0004170894],"domain_scores_gemma":[0.8455194,0.1254923,0.01020134,0.01083314,0.006972677,0.0009811547],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001019409,0.0004168002,0.5726256,0.0001767261,0.003253996,0.0004150381,0.0007883737,0.2759678,0.002239105,0.002784929,0.00133808,0.1389742],"study_design_scores_gemma":[0.00006429191,0.0007283071,0.1039725,0.0000858498,0.0003350035,0.000396981,0.0003454642,0.8808573,0.002729884,0.009467651,0.0009040101,0.0001127225],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7507377,0.00118143,0.2430005,0.0008904353,0.0001254711,0.0002756686,0.0007122022,0.0009584802,0.002118261],"genre_scores_gemma":[0.9524094,0.00008527162,0.04675317,0.00008918374,0.00004538383,0.00008449208,0.0003195285,0.00007604109,0.0001373715],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9376832,"threshold_uncertainty_score":0.3295666,"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."}}