{"id":"W4416041528","doi":"10.1016/j.neucom.2025.132068","title":"A 4D transformer with spatiotemporal attentions for universal diagnosis of brain disorders","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and ICT, South Korea; Institute for Information and Communications Technology Promotion; Electronics and Telecommunications Research Institute","keywords":"Medical diagnosis; Pattern recognition (psychology); Exploit; Neuroimaging; Deep learning; Feature extraction; Temporal resolution","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":[],"consensus_categories":[],"category_scores_codex":[0.00009394962,0.0001128166,0.0001529669,0.0001400659,0.0003675253,0.00002216138,0.0001244093,0.00002559861,0.000004566211],"category_scores_gemma":[0.001250035,0.0001059856,0.00009069135,0.0004633179,0.0001554278,0.0001074729,0.00002382702,0.00009181006,8.013615e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002246333,"about_ca_system_score_gemma":0.00006518614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004157851,"about_ca_topic_score_gemma":0.0001447228,"domain_scores_codex":[0.9991015,0.0000591326,0.0001591953,0.0003536429,0.0001365479,0.000189946],"domain_scores_gemma":[0.9939415,0.005806921,0.00007259395,0.00011223,0.0000452398,0.00002147157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001168198,0.002382951,0.3887823,0.001391601,0.0002992268,0.00001994846,0.002913362,0.02817619,0.1556909,0.221826,0.02834295,0.1690064],"study_design_scores_gemma":[0.01370364,0.003647038,0.2006973,0.0009691223,0.000335059,0.0000221906,0.001771189,0.06195797,0.5324551,0.01397382,0.1688685,0.001599023],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8448552,0.00001279272,0.1225995,0.02908656,0.0002710695,0.0007592578,0.00002657876,0.000105464,0.002283499],"genre_scores_gemma":[0.99704,0.000003841,0.0008521608,0.001854732,0.00002470158,0.00004850043,0.00000140488,0.00001232077,0.0001622759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3767642,"threshold_uncertainty_score":0.4321966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01979098195481485,"score_gpt":0.2666536622075917,"score_spread":0.2468626802527768,"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."}}