{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06806692,0.0002061644,0.0006111187,0.0002901477,0.0002102243,0.00008883937,0.001676679,0.0001757152,0.0002010857],"category_scores_gemma":[0.2542945,0.0001419788,0.00002963809,0.001547309,0.0005495522,0.0001898645,0.001721896,0.003882219,0.000001009939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001095174,"about_ca_system_score_gemma":0.001790955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007247403,"about_ca_topic_score_gemma":0.0001443783,"domain_scores_codex":[0.9592489,0.0352787,0.001145539,0.0009992928,0.002382144,0.0009454454],"domain_scores_gemma":[0.8993601,0.09861114,0.0001996778,0.000868896,0.0006125816,0.0003476097],"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":[0.0001456158,0.0003091747,0.1024609,0.001394478,0.00001961118,0.0002774361,0.002241821,0.0005965804,0.0003110035,0.01890256,0.0000311166,0.8733097],"study_design_scores_gemma":[0.0004521105,0.001123192,0.09781223,0.0005791854,0.000005503387,0.00004924404,0.0002797451,0.8923295,0.0003424877,0.00685678,0.00005617685,0.0001138025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0452567,0.0005145753,0.9528596,0.0006181676,0.00005702348,0.0002817626,0.0001419163,0.00001695063,0.0002533468],"genre_scores_gemma":[0.2884543,0.0001788273,0.7111826,0.00005537251,0.00005217911,0.00002608935,0.00003208412,0.00001225139,0.000006274106],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.891733,"threshold_uncertainty_score":0.9984159,"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."}}