{"id":"W4413932853","doi":"10.1111/ctr.70303","title":"Accuracy, Clarity, and Comprehensiveness of ChatGPT Outputs for Commonly Asked Questions About Living Kidney Donation","year":2025,"lang":"en","type":"article","venue":"Clinical Transplantation","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Kappa; Kidney donation; CLARITY; Cohen's kappa; Kidney; Family medicine; Likert scale; Kidney transplantation; Inter-rater reliability; Donation; Internal medicine; Consistency (knowledge bases); Rating scale; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.06239933,0.0005547971,0.000981637,0.00337438,0.0007722357,0.002078882,0.0009770311,0.001010211,0.002918826],"category_scores_gemma":[0.1967743,0.0002391399,0.001516941,0.001512016,0.00119841,0.001652914,0.002756267,0.0006409736,0.001271794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519567,"about_ca_system_score_gemma":0.001845126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006210358,"about_ca_topic_score_gemma":0.005673425,"domain_scores_codex":[0.9461875,0.03472968,0.006136588,0.003523328,0.007908406,0.001514477],"domain_scores_gemma":[0.7072501,0.2075549,0.0256851,0.0108335,0.04583922,0.002837312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002001031,0.0001587464,0.7873325,0.002855437,0.0004574299,0.0004931586,0.04261732,0.002448754,0.007815157,0.0006753834,0.007646706,0.1454982],"study_design_scores_gemma":[0.0001084889,0.0009396661,0.9361404,0.001905233,0.0004399343,0.00139069,0.01813247,0.01428612,0.008141341,0.001567473,0.01666149,0.0002867103],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9636201,0.001139708,0.01849325,0.001183406,0.000200626,0.0005967615,0.00380854,0.001032769,0.009924782],"genre_scores_gemma":[0.9853122,0.0003419438,0.01063098,0.0004456331,0.00009421794,0.0004930948,0.001821546,0.0001055878,0.0007548099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06239933,"threshold_uncertainty_score":0.3300031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.190274519640396,"score_gpt":0.5057505621121946,"score_spread":0.3154760424717986,"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."}}