{"id":"W4322491365","doi":"10.1038/s43856-023-00262-4","title":"MRI-based deep learning can discriminate between temporal lobe epilepsy, Alzheimer’s disease, and healthy controls","year":2023,"lang":"en","type":"article","venue":"Communications Medicine","topic":"Epilepsy research and treatment","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; National Institute of Mental Health; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Temporal lobe; Epilepsy; Neuroscience; Disease; Psychology; Medicine; Artificial intelligence; Pathology; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.000740382,0.000223012,0.000541909,0.0003532299,0.0005559813,0.00001917958,0.0003701783,0.00006728311,0.00008028228],"category_scores_gemma":[0.0006318405,0.0001703024,0.00007488101,0.0006183831,0.0007938317,0.00005438056,0.0002474712,0.0005598884,0.00007471544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009484396,"about_ca_system_score_gemma":0.0002557579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006031389,"about_ca_topic_score_gemma":0.0002786325,"domain_scores_codex":[0.9979287,0.000383774,0.0004435805,0.0003228139,0.0004322542,0.0004888572],"domain_scores_gemma":[0.9961163,0.001073241,0.0001291536,0.001557281,0.0001743113,0.0009497222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002873267,0.0001938742,0.9616715,0.0001151478,0.0002978407,0.00006772565,0.000471847,0.000009566976,0.00006067628,0.0007090899,0.002780214,0.03333524],"study_design_scores_gemma":[0.007122559,0.001755921,0.9477448,0.0005277278,0.001071729,0.000008321315,0.0009051132,0.007679581,0.00002020919,0.0007661922,0.03218463,0.0002132214],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2133733,0.0504766,0.00101515,0.723035,0.0001578673,0.003839762,0.0001908814,0.0009902855,0.006921151],"genre_scores_gemma":[0.9887094,0.005097244,0.000814026,0.0009650586,0.0001630664,0.0002916822,0.003539081,0.00004208159,0.0003783267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7753361,"threshold_uncertainty_score":0.694473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.108914061947099,"score_gpt":0.3943310425602808,"score_spread":0.2854169806131819,"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."}}