{"id":"W4385898137","doi":"10.1007/s00266-023-03538-1","title":"Complications Following Facelift and Neck Lift: Implementation and Assessment of Large Language Model and Artificial Intelligence (ChatGPT) Performance Across 16 Simulated Patient Presentations","year":2023,"lang":"en","type":"article","venue":"Aesthetic Plastic Surgery","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Psychological intervention; Otorhinolaryngology; Anxiety; Presentation (obstetrics); Differential diagnosis; Health care; Physical therapy; Medical emergency; Surgery; Psychiatry","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":[0.0003414058,0.0001209363,0.0002291402,0.0001570956,0.0002559104,0.00003134287,0.00002764344,0.00005848978,0.00001030367],"category_scores_gemma":[0.0001814638,0.0001178735,0.00003993595,0.0003174944,0.0000879361,0.0001231061,0.00005144871,0.0001122699,0.000005879853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003308807,"about_ca_system_score_gemma":0.0001482586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002583349,"about_ca_topic_score_gemma":0.0001198251,"domain_scores_codex":[0.9986891,0.00003940327,0.0005299484,0.0002514884,0.0002073823,0.0002826354],"domain_scores_gemma":[0.9986424,0.0008455859,0.0001316321,0.0001548112,0.0000947515,0.0001308239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007487432,0.0002766886,0.5139444,0.0003218902,0.00005092212,0.00001138325,0.02600503,0.005902006,0.001237062,0.001021952,0.0002209724,0.4509329],"study_design_scores_gemma":[0.00009742643,0.0002215817,0.3142185,0.0002790965,0.00009096767,0.00003738562,0.03754438,0.6440862,0.002220778,0.0008597526,0.0001118105,0.0002320257],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957824,0.0001500029,0.002572075,0.0007935398,0.0002082395,0.0003728336,0.00004197126,0.0000501266,0.0000287535],"genre_scores_gemma":[0.9990504,0.0003332367,0.0002611318,0.000089513,0.00001576275,0.0000458517,0.0001779357,0.00001530893,0.00001088268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6381842,"threshold_uncertainty_score":0.4806741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1231273372157957,"score_gpt":0.4538290074812418,"score_spread":0.3307016702654461,"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."}}