{"id":"W4414379024","doi":"10.1101/2025.09.19.677393","title":"The Use of Artificial Intelligence In Magnetic Resonance Imaging of Epilepsy: A Systematic Review and Meta-Analysis","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Montreal Neurological Institute and Hospital; University of Toronto; BC Children's Hospital; Montreal Children's Hospital; McGill University","funders":"Canadian Institutes of Health Research; Hospital for Sick Children; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fondation Brain Canada","keywords":"Epilepsy; Magnetic resonance imaging; Temporal lobe; Modality (human–computer interaction); Neuroimaging; Reliability (semiconductor)","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":[],"consensus_categories":[],"category_scores_codex":[0.001338847,0.0002860456,0.00152365,0.0003923217,0.00009254881,0.0001152371,0.0005317671,0.00009862665,0.00002040783],"category_scores_gemma":[0.003462084,0.0002206001,0.0003967047,0.002129781,0.0002922427,0.0001003916,0.000250771,0.000376474,0.000002721142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006385891,"about_ca_system_score_gemma":0.0001590815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004501718,"about_ca_topic_score_gemma":0.00001396321,"domain_scores_codex":[0.9964835,0.0008666732,0.001356037,0.0007225787,0.0003488717,0.0002223391],"domain_scores_gemma":[0.996416,0.000851617,0.0009861201,0.001398569,0.0002897031,0.00005800846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001402596,0.000800827,0.002555579,0.4322205,0.007747913,0.00006009324,0.0001273156,0.0006819538,0.4908612,0.06461129,0.0001202264,0.00007273665],"study_design_scores_gemma":[0.0001830568,0.00008264464,0.02453444,0.01758602,0.2934913,1.048581e-7,0.00002837999,0.04752374,0.6143721,0.0001086282,0.0004630063,0.001626594],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.09293989,0.8402631,0.0335418,0.008810041,0.001491464,0.02006542,0.002250241,0.0006039486,0.00003415048],"genre_scores_gemma":[0.9926327,0.005694635,0.000694158,0.0004498624,0.000007693616,0.0004828624,3.525106e-8,0.00001956688,0.00001852304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8996928,"threshold_uncertainty_score":0.8995812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07492044034282058,"score_gpt":0.2768845607815236,"score_spread":0.201964120438703,"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."}}