{"id":"W4415567131","doi":"10.3389/fnagi.2025.1679788","title":"Multimodal radiomics of cerebellar subregions for machine learning-driven Alzheimer’s disease diagnosis","year":2025,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Northern California Institute for Research and Education; BioClinica; Alzheimer's Disease Neuroimaging Initiative; Bristol-Myers Squibb; Eli Lilly and Company; Biogen; Eisai; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Radiomics; Disease; Neuroimaging; Magnetic resonance imaging; Cerebellum; Biomarker","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":[0.000381254,0.0001794321,0.0004046056,0.0004889381,0.0001819575,0.00003004222,0.0003319243,0.00005086384,0.000003125765],"category_scores_gemma":[0.001963598,0.0001730372,0.000151341,0.0006981507,0.0004549049,0.00009539936,0.00009916769,0.0004594881,3.869721e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006768992,"about_ca_system_score_gemma":0.0002055358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007158136,"about_ca_topic_score_gemma":0.000002066543,"domain_scores_codex":[0.9983823,0.00008110101,0.0003596923,0.0005143411,0.0002592192,0.0004033209],"domain_scores_gemma":[0.9990783,0.0001985043,0.0001280115,0.0003165484,0.00005920545,0.0002193695],"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":[0.0001031767,0.0001772683,0.9727917,0.0001448632,0.00001683211,0.00003530374,0.0001465715,0.008196716,0.001138212,0.0002639907,0.004063806,0.01292153],"study_design_scores_gemma":[0.00169552,0.00009288384,0.1288641,0.0003222334,0.0001593987,0.000006393669,0.00004632784,0.8439409,0.0006993749,0.0003259496,0.02368358,0.0001633598],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.439876,0.007607029,0.5177841,0.02605545,0.005680676,0.002117368,0.00006096564,0.0002493887,0.0005690791],"genre_scores_gemma":[0.973743,0.000818152,0.02313678,0.001684802,0.00005279154,0.00007360848,0.00001781912,0.00002722346,0.0004458117],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8439277,"threshold_uncertainty_score":0.7056251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01736875738736807,"score_gpt":0.2968238335483256,"score_spread":0.2794550761609575,"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."}}