{"id":"W2779764073","doi":"10.1016/j.schres.2017.11.038","title":"Can we accurately classify schizophrenia patients from healthy controls using magnetic resonance imaging and machine learning? A multi-method and multi-dataset study","year":2017,"lang":"en","type":"article","venue":"Schizophrenia Research","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":86,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute; University of Toronto; Centre for Addiction and Mental Health","funders":"National Institute of Mental Health; Alzheimer's Society; Consejo Nacional de Ciencia y Tecnología; Weston Brain Institute; Centre for Addiction and Mental Health Foundation; Canadian Institutes of Health Research; National Alliance for Research on Schizophrenia and Depression; Alzheimer Society; Natural Sciences and Engineering Research Council of Canada; Ontario Mental Health Foundation; Sistema Nacional de Investigadores; Michael J. Fox Foundation for Parkinson's Research","keywords":"Support vector machine; Artificial intelligence; Machine learning; Linear discriminant analysis; Pattern recognition (psychology); Computer science; Logistic regression; Cross-validation; Data set; Regression; Magnetic resonance imaging; Feature (linguistics); Mathematics; Statistics; Medicine; Radiology","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001072046,0.0003716176,0.0006053291,0.0003259952,0.002068104,0.0004135612,0.0004870719,0.0001042866,0.00002213054],"category_scores_gemma":[0.001357774,0.0003364629,0.00004978449,0.0002387362,0.0006124438,0.0002862634,0.0009474356,0.001771282,0.000009313449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001155602,"about_ca_system_score_gemma":0.0002089134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003686706,"about_ca_topic_score_gemma":0.0006834609,"domain_scores_codex":[0.9962427,0.0006114664,0.0005065216,0.001209242,0.0006591543,0.0007708968],"domain_scores_gemma":[0.9970323,0.0004919783,0.0002562896,0.001358271,0.0003438388,0.0005173155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006013323,0.001160673,0.630354,0.00007962812,0.00003171526,0.0001656109,0.0003234414,0.00000334525,0.008023971,0.00008661325,0.0003230009,0.3534346],"study_design_scores_gemma":[0.02952058,0.001109053,0.8588477,0.0002803154,0.0001060896,0.00004955767,0.000205569,0.1022836,0.0002882385,0.0009811384,0.005857625,0.0004705361],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9778983,0.006567687,0.003400488,0.006246496,0.00006851684,0.00337389,0.00224881,0.0001834551,0.00001235998],"genre_scores_gemma":[0.848735,0.0008805704,0.1494542,0.000175993,0.0001126285,0.0001919996,0.0002707097,0.0000851747,0.00009369665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3529641,"threshold_uncertainty_score":0.9999087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2407917029032596,"score_gpt":0.4792996930804956,"score_spread":0.238507990177236,"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."}}