{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001842547,0.0002756369,0.0008051574,0.0009341601,0.0002081372,0.00007894016,0.000629526,0.00007023867,0.00002237836],"category_scores_gemma":[0.002272212,0.0002224476,0.0002759739,0.00125048,0.0007943462,0.0002731329,0.0003455776,0.0004315777,0.000003126874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004152922,"about_ca_system_score_gemma":0.0003607335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002506657,"about_ca_topic_score_gemma":0.002722901,"domain_scores_codex":[0.996989,0.0005263829,0.0009980333,0.0006108452,0.0003213007,0.0005545125],"domain_scores_gemma":[0.9875639,0.01117607,0.0003804915,0.0007034341,0.00009317444,0.00008293368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006134429,0.0003371257,0.3563419,0.0002800921,0.00009487145,0.00008832387,0.01363044,0.002022636,0.0006200148,0.5702409,0.0001698062,0.05556042],"study_design_scores_gemma":[0.0004842093,0.0002291565,0.1547217,0.002996256,0.00008622467,0.00004199166,0.03768917,0.2000638,0.1275016,0.4729958,0.001422005,0.001768029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9475716,0.00537008,0.02996045,0.01099352,0.0004990838,0.0006091886,0.00002637252,0.0001476429,0.004822081],"genre_scores_gemma":[0.9975244,0.001321724,0.0005635782,0.0002260535,0.00002950925,0.00004647825,0.000006186043,0.00001652111,0.0002655293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2016203,"threshold_uncertainty_score":0.9071152,"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."}}