{"id":"W4391254266","doi":"10.2196/54704","title":"A Preliminary Checklist (METRICS) to Standardize the Design and Reporting of Studies on Generative Artificial Intelligence–Based Models in Health Care Education and Practice: Development Study Involving a Literature Review","year":2024,"lang":"en","type":"review","venue":"Interactive Journal of Medical Research","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Checklist; Inter-rater reliability; Scopus; Health care; Systematic review; MEDLINE; Computer science; Psychology; Medical education; Management science; Medicine; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04557042,0.0002977565,0.001998734,0.001750333,0.0001945469,0.0001163449,0.0002591428,0.0002011199,0.000007705482],"category_scores_gemma":[0.1484632,0.0001659369,0.0001522493,0.002183511,0.0001877259,0.0001940791,0.0002023478,0.003534795,0.000001943793],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001894015,"about_ca_system_score_gemma":0.01879146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000102313,"about_ca_topic_score_gemma":0.00005758054,"domain_scores_codex":[0.9865804,0.004622251,0.005185582,0.0004801633,0.002795976,0.0003356198],"domain_scores_gemma":[0.9695148,0.01805146,0.004170364,0.0003902246,0.007229778,0.0006433477],"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":[0.0006330169,0.000646412,0.000002874752,0.05400439,0.0002601837,0.0002532167,0.07006408,0.00001235274,3.010517e-7,0.0000638512,0.001132643,0.8729267],"study_design_scores_gemma":[0.00004302367,0.006230318,0.00000425707,0.783649,0.0004462942,0.0007248019,0.1703784,0.0003581777,0.00005741514,0.0004729979,0.0374671,0.0001681672],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004831604,0.9790921,0.001189595,0.01501158,0.0005286568,0.00367099,0.000002907071,0.000003515586,0.00001751541],"genre_scores_gemma":[0.006988927,0.9879446,0.003622372,0.0006811557,0.0004010488,0.0003061513,0.000006022715,0.00002968382,0.00002006218],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8727585,"threshold_uncertainty_score":0.9987641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6590626657866271,"score_gpt":0.6746638701849532,"score_spread":0.01560120439832613,"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."}}