{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4028058,0.006227401,0.009784038,0.04542559,0.008058979,0.01321284,0.01164221,0.008054833,0.00933698],"category_scores_gemma":[0.5749955,0.006581418,0.01509204,0.02685435,0.007903851,0.01764561,0.01475068,0.01007866,0.005323864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02663361,"about_ca_system_score_gemma":0.1180929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006774989,"about_ca_topic_score_gemma":0.01495726,"domain_scores_codex":[0.5574092,0.188805,0.2110774,0.006995752,0.03132146,0.004391084],"domain_scores_gemma":[0.2727401,0.3075566,0.06758816,0.03516742,0.3075237,0.009424029],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002071946,0.001186102,0.01322195,0.318447,0.001844583,0.001339495,0.02982277,0.003363197,0.006578311,0.02245679,0.2142408,0.385427],"study_design_scores_gemma":[0.00371421,0.002854127,0.03128101,0.3511567,0.003480032,0.00170276,0.0331701,0.005386981,0.006713402,0.03066862,0.5286681,0.001203981],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"methods","genre_scores_codex":[0.01247216,0.01255149,0.1594489,0.02510008,0.004574972,0.7499323,0.0257617,0.003186814,0.006971549],"genre_scores_gemma":[0.006607562,0.003313248,0.456294,0.002292766,0.0002642178,0.5232623,0.006885624,0.0001834446,0.0008967102],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5971942,"threshold_uncertainty_score":0.7364467,"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."}}