{"id":"W2984554569","doi":"10.1111/epi.16380","title":"Learning to see the invisible: A data‐driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy","year":2019,"lang":"en","type":"article","venue":"Epilepsia","topic":"Epilepsy research and treatment","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; National Institute for Health and Care Research","keywords":"Temporal lobe; Laterality; Abnormality; Magnetic resonance imaging; Epilepsy; Psychology; Lateralization of brain function; Hippocampus; Occipital lobe; Radiology; Neuroscience; Medicine; 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":[],"consensus_categories":[],"category_scores_codex":[0.001421892,0.0002712317,0.0004745148,0.0002697573,0.000110152,0.00005911737,0.0006479816,0.00007551888,0.00008662943],"category_scores_gemma":[0.0003037243,0.0001592594,0.00005118191,0.0008822621,0.00007801026,0.0002473123,0.0005201303,0.0006892791,0.00006093542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001691705,"about_ca_system_score_gemma":0.0001832135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001332035,"about_ca_topic_score_gemma":0.0006175778,"domain_scores_codex":[0.9968916,0.0004577875,0.0005270474,0.0006294851,0.0007928971,0.0007011478],"domain_scores_gemma":[0.9980868,0.0004169701,0.0001294146,0.001074454,0.00009735921,0.0001949807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009157735,0.0004758211,0.9865724,0.0001197277,0.00002608699,0.00003107543,0.002337748,0.0007560126,0.00004890629,0.00004749063,0.0003301355,0.008338767],"study_design_scores_gemma":[0.003247736,0.00234813,0.9903639,0.0005200871,0.00001877012,0.00000736871,0.00132711,0.001461497,0.00003829523,0.00000665861,0.00048246,0.0001779677],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944221,0.0001398177,0.0001720597,0.001532936,0.00003623236,0.002546557,0.00007582005,0.00002220332,0.001052318],"genre_scores_gemma":[0.9974052,0.0000179754,0.001148516,0.0005609897,0.0000319774,0.0001258617,0.0002086862,0.00003936234,0.000461452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0081608,"threshold_uncertainty_score":0.6494409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03226381934398043,"score_gpt":0.3103448206137854,"score_spread":0.278081001269805,"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."}}