{"id":"W4412444163","doi":"10.1016/j.jval.2025.04.1272","title":"MSR120 Estimating Sample Size for Training Ensemble Machine Learning Models","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Children's Hospital of Eastern Ontario","funders":"","keywords":"Training (meteorology); Ensemble learning; Computer science; Machine learning; Sample (material); Artificial intelligence; Sample size determination; Statistics; Mathematics; Geography; Chemistry; Chromatography","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":[],"consensus_categories":[],"category_scores_codex":[0.002046893,0.0001204743,0.0002317781,0.0001592758,0.0003299208,0.0001087273,0.0004256128,0.0000500333,0.00000303187],"category_scores_gemma":[0.002035727,0.0001237702,0.00004194383,0.0004749532,0.00001360674,0.0002757005,0.0001019832,0.0003183828,0.000003632159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00011683,"about_ca_system_score_gemma":0.0003600243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004665253,"about_ca_topic_score_gemma":0.00006230322,"domain_scores_codex":[0.9983059,0.0002870086,0.0004381266,0.0004293268,0.0001473294,0.0003923706],"domain_scores_gemma":[0.9965425,0.002809849,0.0001786239,0.0003571898,0.00003699978,0.00007481403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007438635,0.00002689442,0.001191304,0.0002097309,0.000005028542,4.571882e-7,0.002151968,0.6329671,0.00004065708,0.178125,0.0001249797,0.1851494],"study_design_scores_gemma":[0.0003503382,0.00006763106,0.0004920779,0.0001594596,0.000001628099,0.000001679184,0.0000625688,0.9339303,0.00001048407,0.0613386,0.003492929,0.00009229801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002148915,0.0003250125,0.9891714,0.006702873,0.0002909042,0.0002977167,0.0000081107,0.0002229613,0.0008321247],"genre_scores_gemma":[0.4042074,0.00001976925,0.5949642,0.0005126921,0.00003728334,0.00003726757,0.00001971936,0.000008070671,0.000193645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4020585,"threshold_uncertainty_score":0.7052498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1154228437099247,"score_gpt":0.3413086162258021,"score_spread":0.2258857725158773,"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."}}