{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006147175,0.0005756071,0.001133654,0.001015247,0.0004788677,0.0007638828,0.001272343,0.001174216,0.003679788],"category_scores_gemma":[0.04330021,0.0005006123,0.0007954214,0.0005892054,0.0002729479,0.001292209,0.001046785,0.00156099,0.00118441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005944219,"about_ca_system_score_gemma":0.001193411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003721153,"about_ca_topic_score_gemma":0.004595244,"domain_scores_codex":[0.9977736,0.001120095,0.000156421,0.0003543905,0.0004703507,0.000125245],"domain_scores_gemma":[0.9830467,0.01215018,0.0003912531,0.00167401,0.002561976,0.000175791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001404422,0.0003582037,0.0146159,0.00016051,0.0002631473,0.0001139615,0.0001596689,0.3025748,0.01171555,0.007114498,0.009692285,0.651827],"study_design_scores_gemma":[0.00003426848,0.00008775735,0.001482868,0.00001916847,0.00002145236,0.00003701372,0.00001650013,0.9915387,0.003257045,0.002681761,0.0008156749,0.000007796667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1031466,0.0004699707,0.8909307,0.0003567415,0.000167785,0.0001571867,0.0004147291,0.002547438,0.00180883],"genre_scores_gemma":[0.5266533,0.0001950005,0.4678847,0.0002044174,0.0001728754,0.0004739319,0.001757454,0.0003792862,0.002279031],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006147175,"threshold_uncertainty_score":0.03250974,"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."}}