{"id":"W4379140845","doi":"10.1016/j.jpurol.2023.05.018","title":"ChatGPT and large language model (LLM) chatbots: The current state of acceptability and a proposal for guidelines on utilization in academic medicine","year":2023,"lang":"en","type":"review","venue":"Journal of Pediatric Urology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":214,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Medicine; Guideline; MEDLINE; English language; Medical record; Medical education; Artificial intelligence; Computer science; Pathology; Psychology; Internal medicine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01484546,0.0008964271,0.00349771,0.004318078,0.0006782124,0.004524268,0.002833702,0.003001398,0.01348031],"category_scores_gemma":[0.02771509,0.0006823123,0.002153915,0.003703609,0.001958622,0.006046029,0.003251623,0.005222072,0.003515467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003027317,"about_ca_system_score_gemma":0.007919611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006069463,"about_ca_topic_score_gemma":0.008698822,"domain_scores_codex":[0.9951175,0.00212452,0.0006937595,0.000508359,0.001251729,0.0003040779],"domain_scores_gemma":[0.9614266,0.03333491,0.001882435,0.0005280355,0.002124148,0.0007037657],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002835535,0.0001302596,0.0002711769,0.03347968,0.0001423948,0.0000621883,0.000263201,0.0001814751,0.0003484843,0.005763755,0.01497692,0.9440969],"study_design_scores_gemma":[0.0003074536,0.0007547426,0.002825195,0.08528133,0.0009634336,0.001075866,0.0007447941,0.0008908754,0.001335877,0.005852396,0.8998348,0.0001332301],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003825011,0.994067,0.001317448,0.001703663,0.0003709779,0.00007292778,0.0001041644,0.00008199953,0.001899408],"genre_scores_gemma":[0.007542231,0.9764717,0.008363893,0.004120419,0.0004087882,0.0004548228,0.0003297571,0.00007048422,0.002237928],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9851546,"threshold_uncertainty_score":0.07851124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.455626065115204,"score_gpt":0.5717565975105738,"score_spread":0.1161305323953699,"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."}}