{"id":"W2124200703","doi":"10.1177/0962280213502437","title":"A comparison of machine learning methods for classification using simulation with multiple real data examples from mental health studies","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Menzies Centre for Australian Studies, King's College London, University of London; University of California, San Diego; Canadian Institutes of Health Research; University of California, Los Angeles; National Institutes of Health; Genentech; IXICO; Servier; King's College London; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Eisai; Synarc; South London and Maudsley NHS Foundation Trust; Pfizer; Biogen; BioClinica; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Alzheimer's Association; Amorfix Life Sciences; Bayer HealthCare; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation","keywords":"Computer science; Sample size determination; Support vector machine; Artificial intelligence; Linear discriminant analysis; Machine learning; Random forest; Kernel (algebra); Sample (material); Stability (learning theory); Feature (linguistics); Kernel method; Pattern recognition (psychology); Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02994441,0.0001874213,0.0008433367,0.0003373449,0.0003524427,0.00003397942,0.0007122235,0.000208303,0.00191312],"category_scores_gemma":[0.0526082,0.0001467853,0.00002555148,0.0006037927,0.001090869,0.00013184,0.0005644981,0.001552958,0.00001206277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004584335,"about_ca_system_score_gemma":0.0005302451,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01887414,"about_ca_topic_score_gemma":0.001057188,"domain_scores_codex":[0.9747983,0.02037212,0.001271574,0.0008796236,0.001645405,0.001033036],"domain_scores_gemma":[0.9087705,0.08910696,0.0002572823,0.0007655952,0.0004743043,0.0006253733],"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":[0.0007296202,0.0004899923,0.02216776,0.0004170019,0.00009760774,0.000002972297,0.003535705,0.00003776604,0.001048041,0.005128173,0.0006264671,0.9657189],"study_design_scores_gemma":[0.001620232,0.001017769,0.03238528,0.0002423136,0.000008909223,0.000001254573,0.008283837,0.9455897,0.00009184272,0.007027495,0.00360817,0.0001231686],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01195155,0.001891722,0.9812484,0.001815532,0.0002058464,0.002293427,0.0003744306,0.00002597066,0.0001931242],"genre_scores_gemma":[0.0931351,0.0002676569,0.9053603,0.00005452193,0.0001048889,0.0002843631,0.0006924045,0.00003733836,0.0000633898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9655957,"threshold_uncertainty_score":0.9989992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8484463315588613,"score_gpt":0.7874845120641984,"score_spread":0.06096181949466284,"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."}}