{"id":"W2806322961","doi":"10.1016/j.nicl.2018.08.019","title":"Structural neuroimaging as clinical predictor: A review of machine learning applications","year":2018,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":184,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Fondation Brain Canada","keywords":"Neuroimaging; Functional magnetic resonance imaging; Magnetic resonance imaging; Brain disease; Disease; Medical imaging","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001584643,0.0002233332,0.0005212129,0.00008678257,0.0002869533,0.00004729478,0.0006090616,0.0001128533,0.0006322557],"category_scores_gemma":[0.01469137,0.0002047861,0.0003789813,0.000605002,0.001310227,0.0002093269,0.0002061589,0.001169558,0.0005938448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000145617,"about_ca_system_score_gemma":0.0001179091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005359499,"about_ca_topic_score_gemma":0.000001757054,"domain_scores_codex":[0.9947167,0.001646417,0.001776944,0.001062274,0.0004820382,0.000315626],"domain_scores_gemma":[0.9958984,0.001942255,0.0007814715,0.0008920686,0.0002218291,0.000263993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009037912,0.001843399,0.1982782,0.002942286,0.00006678051,0.0001573469,0.0001804457,0.000006077098,0.1405423,0.01142971,0.01838465,0.6252649],"study_design_scores_gemma":[0.003266907,0.003563336,0.2378738,0.001141838,0.0002579631,0.0007577198,0.00002924098,0.03359352,0.01543354,0.001851762,0.7012569,0.0009734508],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9049408,0.002500628,0.005742038,0.01562177,0.006465114,0.004113236,0.0001219317,0.001951569,0.05854286],"genre_scores_gemma":[0.9786664,0.005339047,0.0003290176,0.01374667,0.001028173,0.00004857226,0.00001069853,0.00005307964,0.0007782939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6828722,"threshold_uncertainty_score":0.9936083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1205252195923044,"score_gpt":0.4213833487128944,"score_spread":0.30085812912059,"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."}}