{"id":"W3096756677","doi":"10.1002/lt.25930","title":"Identifying Modifiable Predictors of Long‐Term Survival in Liver Transplant Recipients With Diabetes Mellitus Using Machine Learning","year":2020,"lang":"en","type":"article","venue":"Liver Transplantation","topic":"Renal Transplantation Outcomes and Treatments","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; SickKids Foundation; Vector Institute; University of Toronto","funders":"Canadian Institute for Advanced Research","keywords":"Medicine; Internal medicine; Diabetes mellitus; Confidence interval; Creatinine; Liver transplantation; Proportional hazards model; Cohort; Transplantation; Gastroenterology; Endocrinology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001065136,0.0002454278,0.00044044,0.0001745691,0.00006906802,0.00002019897,0.00007938768,0.0000909176,0.00008118425],"category_scores_gemma":[0.000003738538,0.0002034657,0.000103055,0.0003466558,0.0000527431,0.0002962666,0.000004064901,0.0002369427,0.000007947734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005120305,"about_ca_system_score_gemma":0.0000432691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004280235,"about_ca_topic_score_gemma":0.0001274589,"domain_scores_codex":[0.9983597,0.0001060865,0.0004361297,0.0003513333,0.000455683,0.0002911086],"domain_scores_gemma":[0.9994495,0.00009168499,0.0001411928,0.00009883241,0.00005786015,0.000160944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001728206,0.0001677813,0.9745505,0.002493144,0.0002739138,0.001095717,0.007250187,0.003772345,0.008268756,0.00001513674,7.981654e-8,0.0003842435],"study_design_scores_gemma":[0.006870394,0.0006033461,0.9261439,0.002460839,0.001204621,0.00007790922,0.00007604602,0.02383919,0.03847613,0.00000258303,0.00000165508,0.0002433404],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874708,0.0006805781,0.01090376,0.00002581178,0.00009300182,0.0004750059,0.0001466066,0.00005391512,0.0001504892],"genre_scores_gemma":[0.9939559,0.003622486,0.001495722,0.0000415459,0.00003790487,0.00001114172,0.0007672738,0.00003613698,0.00003187527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04840655,"threshold_uncertainty_score":0.8297091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0406873816133184,"score_gpt":0.2687400415447682,"score_spread":0.2280526599314498,"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."}}