{"id":"W3135714805","doi":"10.1016/j.pscychresns.2021.111270","title":"Brain age prediction in schizophrenia: Does the choice of machine learning algorithm matter?","year":2021,"lang":"en","type":"article","venue":"Psychiatry Research Neuroimaging","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vancouver Coastal Health; University of British Columbia","funders":"National Institute of Mental Health","keywords":"Regression; Schizophrenia (object-oriented programming); Algorithm; Artificial intelligence; Support vector machine; Linear regression; Regression analysis; Machine learning; Statistics; Ordinary least squares; Psychology; Mathematics; Computer science; Psychiatry","routes":{"ca_aff":true,"ca_fund":false,"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"],"consensus_categories":[],"category_scores_codex":[0.001490628,0.0001824559,0.0002341685,0.0003724187,0.0006875262,0.0001504632,0.0004415405,0.00004155243,0.0001517672],"category_scores_gemma":[0.01688783,0.0001347647,0.00009845741,0.001795576,0.0004337997,0.0003170598,0.0005559247,0.001716021,0.00006796887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006079681,"about_ca_system_score_gemma":0.0001709676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002347841,"about_ca_topic_score_gemma":0.000407144,"domain_scores_codex":[0.9951504,0.002036692,0.0003649508,0.0008391448,0.001017112,0.000591729],"domain_scores_gemma":[0.9878725,0.01131326,0.00009170873,0.0005041165,0.0001466902,0.0000716495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001953987,0.0005758286,0.6942294,0.0002637387,0.00003483705,0.0002745478,0.0008684335,0.000562006,0.2592529,0.001610908,0.02420054,0.01793147],"study_design_scores_gemma":[0.0037361,0.0003631538,0.8321407,0.0004144011,0.00002432894,0.0003460824,0.001788131,0.05702102,0.03050969,0.01676598,0.0562738,0.0006165936],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7677037,0.001087585,0.0004914122,0.2193268,0.002600906,0.0006537731,0.0001123716,0.0001705053,0.00785291],"genre_scores_gemma":[0.992089,0.000114956,0.0008072576,0.003629547,0.0005106798,0.00007338853,0.00000816621,0.00005888048,0.002708072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2287433,"threshold_uncertainty_score":0.9913933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06079151808440129,"score_gpt":0.3485577845482489,"score_spread":0.2877662664638476,"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."}}