{"id":"W4406882679","doi":"10.1007/s00423-025-03626-7","title":"Can surgeons trust AI? Perspectives on machine learning in surgery and the importance of eXplainable Artificial Intelligence (XAI)","year":2025,"lang":"en","type":"article","venue":"Langenbeck s Archives of Surgery","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Transparency (behavior); Artificial intelligence; Vascular surgery; Computer science; Machine learning; Medicine; Cardiac surgery; Surgery","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":[0.01166929,0.0004524718,0.0005346498,0.001818275,0.001149445,0.005356488,0.001162828,0.003126447,0.003217767],"category_scores_gemma":[0.02293901,0.0003099659,0.0005941143,0.001141417,0.02340331,0.007717387,0.002814626,0.005439502,0.0004253636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002971322,"about_ca_system_score_gemma":0.002605865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002152332,"about_ca_topic_score_gemma":0.001430249,"domain_scores_codex":[0.9951893,0.003129475,0.0002277887,0.0003690752,0.0007640924,0.000320164],"domain_scores_gemma":[0.9725068,0.02254555,0.001842647,0.001553528,0.0010632,0.0004882807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002685409,0.00001934993,0.001060423,0.0002269491,0.00003058859,0.0002157777,0.002112767,0.002383655,0.0001531537,0.9646986,0.002340039,0.0267319],"study_design_scores_gemma":[0.000006111374,0.00001894728,0.0005246666,0.0001608201,0.000006472694,0.000132513,0.0005195294,0.002060294,0.00010074,0.9853623,0.01109329,0.00001432471],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03566983,0.08322337,0.1996056,0.5866006,0.002545622,0.00007205792,0.0002056715,0.0002377477,0.09183952],"genre_scores_gemma":[0.9239479,0.02859639,0.02899194,0.01180532,0.002331731,0.00009686768,0.00007406103,0.00006284171,0.004092969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01166929,"threshold_uncertainty_score":0.06171387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03252844417459558,"score_gpt":0.2682100963248586,"score_spread":0.235681652150263,"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."}}