{"id":"W4401851647","doi":"10.1111/medu.15495","title":"<i>Medical Education</i> and artificial intelligence: Responsible and effective practice requires human oversight","year":2024,"lang":"en","type":"editorial","venue":"Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Guard (computer science); Confession (law); Publishing; Psychology; Statement (logic); Public relations; Engineering ethics; Internet privacy; Computer science; Political science; Law; Engineering","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":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00297256,0.0004367511,0.0006211651,0.0005637806,0.0003788011,0.0002158674,0.0002259475,0.002137543,0.001070663],"category_scores_gemma":[0.08210307,0.0003969935,0.0001028745,0.0005848097,0.0006842228,0.0003248202,0.0001588104,0.002704466,0.0002205292],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005657717,"about_ca_system_score_gemma":0.04139306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00235023,"about_ca_topic_score_gemma":0.0003509521,"domain_scores_codex":[0.9944268,0.0004636749,0.00111617,0.001055205,0.002480332,0.000457851],"domain_scores_gemma":[0.9918976,0.004427624,0.0003704071,0.0005888045,0.001428862,0.001286672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000204091,0.0009097637,0.0000417147,0.0009271366,0.00005616111,0.00001865639,0.002155009,2.725042e-8,0.00001344058,0.004031812,0.6918092,0.299833],"study_design_scores_gemma":[0.00004225323,0.0006260637,0.00004252531,0.003861777,0.0004694433,0.000214991,0.00490812,0.000117903,0.0003043255,0.01795104,0.9710972,0.0003643909],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.01043027,0.01285268,0.0001369025,0.139689,0.8306934,0.001722415,0.00001767844,0.0001800812,0.004277675],"genre_scores_gemma":[0.02431255,0.007393003,0.0008090882,0.01074933,0.9485638,0.0008343883,0.001314911,0.0001414469,0.005881458],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.2994686,"threshold_uncertainty_score":0.9998482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03593697362016963,"score_gpt":0.4674283111799274,"score_spread":0.4314913375597578,"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."}}