{"id":"W4412851226","doi":"10.1016/j.ajt.2025.07.2269","title":"A Confounder Debiasing Method for RCT-Like Comparability Enables Machine Learning-Based Personalization of Living Donor Liver Transplantation Survival Benefit","year":2025,"lang":"en","type":"article","venue":"American Journal of Transplantation","topic":"Organ Transplantation Techniques and Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre; University of Toronto","funders":"","keywords":"Medicine; Comparability; Randomized controlled trial; Debiasing; Confounding; Transplantation; Living donor liver transplantation; Personalization; Liver transplantation; Surgery; Internal medicine; Computer science; World Wide Web; Social psychology","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":[0.2078865,0.001752905,0.005241022,0.003437367,0.001765368,0.004822455,0.002986972,0.005241551,0.03779517],"category_scores_gemma":[0.5159686,0.001162529,0.00766799,0.003283973,0.003708509,0.005422791,0.005030786,0.00554464,0.003336046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009755823,"about_ca_system_score_gemma":0.002043384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006208769,"about_ca_topic_score_gemma":0.0006730439,"domain_scores_codex":[0.7121675,0.2243347,0.02326086,0.02853448,0.009525382,0.002177072],"domain_scores_gemma":[0.4632252,0.3854024,0.02235682,0.1200224,0.007458495,0.001534642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.04250452,0.002119247,0.08004931,0.01177873,0.06112905,0.001474568,0.003405828,0.01410853,0.01630125,0.105194,0.02869942,0.6332355],"study_design_scores_gemma":[0.03020978,0.01734967,0.1151188,0.003175224,0.04771934,0.003008123,0.00159135,0.19946,0.03430822,0.3971829,0.1496507,0.001225913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05782342,0.003423751,0.9089034,0.002992292,0.002962231,0.006588159,0.005352183,0.003267041,0.008687526],"genre_scores_gemma":[0.7044804,0.0004424056,0.267377,0.002671522,0.0009924949,0.01651129,0.002432013,0.000842428,0.004250426],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2078865,"threshold_uncertainty_score":0.976817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01743820035843833,"score_gpt":0.3158225698233375,"score_spread":0.2983843694648992,"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."}}