{"id":"W7116853221","doi":"10.1371/journal.pdig.0001155","title":"Autism spectrum disorder detection using diffusion tensor imaging and machine learning","year":2025,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Agence Universitaire de la Francophonie; University of Edinburgh; Mrs Gladys Row Fogo Charitable Trust","keywords":"Diffusion MRI; Fractional anisotropy; Autism spectrum disorder; Support vector machine; Neuroimaging; Pattern recognition (psychology); White matter; Generalization; Random forest; Anisotropy","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":[0.00003847924,0.000107472,0.000171118,0.0001246448,0.0002677223,0.0000432073,0.00003018811,0.00002021733,0.000003428102],"category_scores_gemma":[0.00004203919,0.00009896448,0.00002897301,0.0002104283,0.00004563915,0.0001374011,0.00006991378,0.0002340644,0.000002041664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009886709,"about_ca_system_score_gemma":0.00004337394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009699821,"about_ca_topic_score_gemma":0.000007029179,"domain_scores_codex":[0.9992543,0.00001199717,0.0001809217,0.000253908,0.00008895677,0.0002099447],"domain_scores_gemma":[0.9996525,0.00003436286,0.00006676452,0.000145625,0.00001261179,0.00008815581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008880442,0.0004841975,0.6398603,0.0005236935,0.00002093149,0.00001286291,0.0001131486,0.00002769541,0.005831365,0.002655155,0.00003523868,0.3503466],"study_design_scores_gemma":[0.003139336,0.000705654,0.3791504,0.001828821,0.0001246582,0.000527252,0.0002906667,0.5300413,0.003879057,0.03065965,0.04898194,0.0006713402],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8411918,0.001109079,0.1386791,0.01647012,0.00004008178,0.0006418695,0.00001467658,0.0005840201,0.001269256],"genre_scores_gemma":[0.9967409,0.0002289212,0.001828918,0.0006876435,0.00002098932,0.00001179974,0.00001759196,0.00002104768,0.000442133],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5300136,"threshold_uncertainty_score":0.4035654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03973981842652238,"score_gpt":0.3362264295065378,"score_spread":0.2964866110800154,"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."}}