{"id":"W4396574587","doi":"10.2196/52508","title":"Consolidated Reporting Guidelines for Prognostic and Diagnostic Machine Learning Models (CREMLS)","year":2024,"lang":"en","type":"editorial","venue":"Journal of Medical Internet Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; Children's Hospital of Eastern Ontario; JMIR Publications; University of Ottawa","funders":"","keywords":"Computer science; Machine learning; Medical physics; Artificial intelligence; 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":["metaresearch"],"category_scores_codex":[0.508894,0.004452265,0.008485452,0.03020922,0.005889393,0.0253781,0.01343186,0.0207282,0.02865737],"category_scores_gemma":[0.8342867,0.005409155,0.01266514,0.02237363,0.01027871,0.0120809,0.01251407,0.02425886,0.02628681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008621945,"about_ca_system_score_gemma":0.06299672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00529287,"about_ca_topic_score_gemma":0.003520098,"domain_scores_codex":[0.2856939,0.3439627,0.3002459,0.008042039,0.05726055,0.004794903],"domain_scores_gemma":[0.07654787,0.4190934,0.1306781,0.06158539,0.3070022,0.005092992],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005737487,0.000144962,0.001194798,0.03228757,0.0005488372,0.0002955213,0.001437573,0.0009038157,0.0005467324,0.0167375,0.815661,0.1296679],"study_design_scores_gemma":[0.0007747316,0.0002353147,0.002135044,0.06333728,0.0006351886,0.0006343774,0.0009074199,0.002246623,0.00158335,0.02123616,0.9059026,0.0003718676],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"editorial","genre_scores_codex":[0.002051445,0.05506704,0.3400052,0.2355451,0.1694801,0.09532882,0.05387538,0.01441598,0.03423091],"genre_scores_gemma":[0.01639933,0.04808981,0.5493734,0.06852289,0.03741563,0.2195257,0.04100123,0.004937883,0.01473409],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.491106,"threshold_uncertainty_score":0.6056212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2206807841532813,"score_gpt":0.5126290570624917,"score_spread":0.2919482729092104,"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."}}