{"id":"W4410799588","doi":"10.1016/j.jhep.2025.04.040","title":"Personalized survival benefit estimation from living donor liver transplantation with a novel machine learning method for confounding adjustment","year":2025,"lang":"en","type":"article","venue":"Journal of Hepatology","topic":"Organ Transplantation Techniques and Outcomes","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Rehabilitation Institute; Princess Margaret Cancer Centre; Toronto General Hospital; McGill University Health Centre; University Health Network","funders":"Canadian Institutes of Health Research; Toronto General and Western Hospital Foundation","keywords":"Confounding; Estimation; Living donor liver transplantation; Liver transplantation; Transplantation; Medicine; Computer science; Artificial intelligence; Internal medicine; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004624994,0.000657346,0.001334539,0.0006220251,0.0003854105,0.0009122308,0.001030496,0.0008699272,0.001742302],"category_scores_gemma":[0.01182747,0.0003724063,0.001277578,0.0006175387,0.0002575802,0.0007189709,0.0009860435,0.001640426,0.0002962716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003235959,"about_ca_system_score_gemma":0.001298913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002425103,"about_ca_topic_score_gemma":0.002330611,"domain_scores_codex":[0.998415,0.0009133368,0.00009029583,0.0003364366,0.0001548225,0.00009008629],"domain_scores_gemma":[0.9946854,0.004231349,0.0003128551,0.0004389368,0.0002403543,0.00009108005],"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":[0.00208408,0.0005095892,0.08653051,0.0002481054,0.001608176,0.0004789006,0.000126358,0.3326267,0.004649836,0.01119747,0.006930561,0.5530096],"study_design_scores_gemma":[0.0001006775,0.00009752217,0.005686826,0.0000137411,0.0001573339,0.0001294655,0.000008016367,0.9845161,0.0007007819,0.007612246,0.0009537452,0.00002361716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07407305,0.0009900499,0.9221098,0.0009624336,0.0001797984,0.00006905623,0.0004524736,0.0006558618,0.0005074484],"genre_scores_gemma":[0.814074,0.0004522708,0.1809223,0.0004596008,0.0006091549,0.0001617565,0.001154071,0.0001001099,0.002066785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004624994,"threshold_uncertainty_score":0.0244596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02052748367725801,"score_gpt":0.3266748564974589,"score_spread":0.3061473728202009,"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."}}