{"id":"W3156127058","doi":"10.1177/09622802211002867","title":"Predictive performance of machine and statistical learning methods: Impact of data-generating processes on external validity in the “large N, small p” setting","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Center for Advancing Translational Sciences; Canadian Institutes of Health Research; National Institutes of Health; Ontario Ministry of Health and Long-Term Care; Georgia Clinical and Translational Science Alliance; Heart and Stroke Foundation of Canada","keywords":"Brier score; Machine learning; Random forest; Artificial intelligence; Logistic regression; Lasso (programming language); Computer science; Regression; Statistic; Gradient boosting; Sample size determination; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"category_scores_codex":[0.1451011,0.001176938,0.001181748,0.00140519,0.001493072,0.002809374,0.002221342,0.002363578,0.000724477],"category_scores_gemma":[0.3570767,0.0006320541,0.001502978,0.001255052,0.005995093,0.004424081,0.00318452,0.003757482,0.0001856837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001561931,"about_ca_system_score_gemma":0.002456919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00379019,"about_ca_topic_score_gemma":0.002039225,"domain_scores_codex":[0.9311699,0.05540435,0.002346374,0.004847667,0.005289988,0.000941621],"domain_scores_gemma":[0.4607682,0.4873554,0.01490374,0.02859732,0.007024448,0.001350829],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002217543,0.0005542612,0.2337406,0.0004238366,0.00123978,0.0007032985,0.0008341354,0.6602946,0.001868096,0.03492343,0.0018956,0.06130481],"study_design_scores_gemma":[0.0002011194,0.0006120049,0.01885801,0.0001339038,0.0001112006,0.0002112079,0.0001933464,0.9416933,0.004119608,0.0330283,0.0007711488,0.00006677005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6653413,0.001930018,0.3248189,0.003156913,0.0002222953,0.0005494886,0.0005218197,0.0004560691,0.003003215],"genre_scores_gemma":[0.9690702,0.0001704086,0.02956072,0.0003428518,0.00005527337,0.0002008176,0.0003670797,0.00005084694,0.0001818964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8548989,"threshold_uncertainty_score":0.7673774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2592234766623989,"score_gpt":0.6037200504579326,"score_spread":0.3444965737955338,"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."}}