{"id":"W4289653886","doi":"10.1101/2022.08.01.502396","title":"RELIEF: a structured multivariate approach for removal of latent inter-scanner effects","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Addiction and Mental Health; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Mental Health; University of Toronto; Canadian Institutes of Health Research; Centre for Addiction and Mental Health Foundation","keywords":"Scanner; Generalizability theory; Computer science; Harmonization; Univariate; Multivariate statistics; Data science; Artificial intelligence; Machine learning; Data mining; 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":[],"consensus_categories":[],"category_scores_codex":[0.01118141,0.001677845,0.001944496,0.002006885,0.0007607721,0.001371139,0.003139467,0.001464494,0.005827176],"category_scores_gemma":[0.02427803,0.0009779172,0.003112892,0.002186622,0.001719159,0.001948478,0.003685671,0.002607036,0.001775197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004423161,"about_ca_system_score_gemma":0.001738756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001629365,"about_ca_topic_score_gemma":0.002376419,"domain_scores_codex":[0.9933974,0.004175269,0.0002821671,0.001103402,0.0007635488,0.0002782154],"domain_scores_gemma":[0.9874482,0.007044248,0.001293841,0.002571955,0.001321122,0.0003208213],"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":[0.0008321697,0.0003995759,0.006922946,0.001026234,0.001581664,0.0006383997,0.0008704101,0.2080795,0.02063588,0.05114814,0.02480542,0.6830596],"study_design_scores_gemma":[0.0001708547,0.0003344146,0.00338154,0.00009160224,0.0002397505,0.0003403274,0.0001749766,0.9170015,0.006003599,0.05891168,0.01321392,0.0001357799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003123685,0.0001472779,0.99538,0.0001347093,0.0000259914,0.00005825522,0.0001599728,0.0008068889,0.0001632844],"genre_scores_gemma":[0.08577636,0.0002581991,0.9095976,0.0003531176,0.0002073021,0.0004953474,0.00123812,0.0008112981,0.001262768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01118141,"threshold_uncertainty_score":0.05913365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03422065117062607,"score_gpt":0.2929011877885035,"score_spread":0.2586805366178775,"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."}}