{"id":"W4391723380","doi":"10.1016/j.ejso.2024.108014","title":"A foundation for evaluating the surgical artificial intelligence literature","year":2024,"lang":"en","type":"review","venue":"European Journal of Surgical Oncology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network","funders":"","keywords":"Generalizability theory; Foundation (evidence); Glossary; Computer science; Management science; Quality (philosophy); Artificial intelligence; Data science; Psychology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02823138,0.002186597,0.005894831,0.03668718,0.002710097,0.01079603,0.003885233,0.004956962,0.007132682],"category_scores_gemma":[0.06810353,0.0009282999,0.002683954,0.01582237,0.003665873,0.01653124,0.00572578,0.006164716,0.002309416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0065294,"about_ca_system_score_gemma":0.02223396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006204943,"about_ca_topic_score_gemma":0.01182766,"domain_scores_codex":[0.9900767,0.002865586,0.003230169,0.0007895487,0.002607351,0.0004306442],"domain_scores_gemma":[0.9173946,0.04525853,0.00792806,0.00224671,0.0243375,0.002834494],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002742416,0.0002130561,0.002436718,0.1307529,0.001327824,0.0004081857,0.0009607722,0.0006794436,0.00115791,0.04140613,0.08275345,0.7376294],"study_design_scores_gemma":[0.0001132197,0.000276892,0.003958063,0.3235579,0.002883459,0.0007314812,0.002381499,0.0007200384,0.0003178372,0.03415431,0.6307854,0.0001199642],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004090661,0.9765222,0.001109759,0.01605837,0.002938174,0.0001800202,0.0001871573,0.00005069677,0.002544579],"genre_scores_gemma":[0.008740718,0.9590117,0.01684282,0.01070125,0.002683975,0.0004825265,0.0005907552,0.00004351142,0.0009026702],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9717686,"threshold_uncertainty_score":0.1493036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5205678886691746,"score_gpt":0.5828423024108212,"score_spread":0.06227441374164666,"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."}}