{"id":"W4393128858","doi":"10.1016/j.soard.2024.03.011","title":"Harnessing artificial intelligence in bariatric surgery: comparative analysis of ChatGPT-4, Bing, and Bard in generating clinician-level bariatric surgery recommendations","year":2024,"lang":"en","type":"review","venue":"Surgery for Obesity and Related Diseases","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Readability; Medicine; Likert scale; Surgery; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002614281,0.0004875478,0.003938113,0.00527596,0.0002492052,0.000101934,0.00007415259,0.0006048423,0.00007112113],"category_scores_gemma":[0.002294492,0.0004287031,0.001272207,0.005750758,0.0001767631,0.0002146468,0.00006387426,0.0006310521,0.000008231052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001997281,"about_ca_system_score_gemma":0.001898362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000896999,"about_ca_topic_score_gemma":0.0005403213,"domain_scores_codex":[0.994415,0.0006128309,0.003372479,0.0008592497,0.0002427755,0.0004976364],"domain_scores_gemma":[0.9864833,0.01178802,0.0009246025,0.0003081337,0.0002176105,0.0002783219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00008537883,0.0005305235,0.04494983,0.0131271,0.0009332191,0.00003587301,0.000800184,0.00007110247,2.239152e-7,0.000166315,0.0006040598,0.9386962],"study_design_scores_gemma":[0.0003696966,0.0006098268,0.1068838,0.2995189,0.2415618,0.000293506,0.02193602,0.2101696,0.0001068401,0.0214604,0.08664307,0.01044657],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.06982445,0.926649,0.0001933923,0.0002734221,0.001530003,0.001077027,0.0003962812,0.00004559162,0.00001087731],"genre_scores_gemma":[0.1174478,0.8799513,0.0001086101,0.00003467889,0.0002369866,0.0001580752,0.001993496,0.00003602191,0.00003299061],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9282496,"threshold_uncertainty_score":0.9998165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3174517299173116,"score_gpt":0.4613307091438424,"score_spread":0.1438789792265309,"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."}}