{"id":"W4413035771","doi":"10.1186/s13195-025-01827-2","title":"Longitudinal structural MRI-based deep learning and radiomics features for predicting Alzheimer’s disease progression","year":2025,"lang":"en","type":"article","venue":"Alzheimer s Research & Therapy","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Geriatric psychiatry; Neurology; Disease; Medicine; Radiomics; Artificial intelligence; Internal medicine; Psychiatry; Radiology; Computer science","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":[0.001662179,0.0002891925,0.0004180232,0.0004623698,0.0009468918,0.0002062745,0.0002435491,0.0001420297,0.00004864573],"category_scores_gemma":[0.0008471627,0.0002237258,0.0001653929,0.0004775508,0.0005462914,0.0001279486,0.0001104445,0.001438779,0.000002098441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005248638,"about_ca_system_score_gemma":0.0003745778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006457748,"about_ca_topic_score_gemma":0.000004350955,"domain_scores_codex":[0.9970477,0.0003440739,0.0003368319,0.0006949791,0.0007495881,0.0008268643],"domain_scores_gemma":[0.9977347,0.0009346224,0.00009079773,0.0003495071,0.0003723256,0.0005180901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004126188,0.0001317156,0.2859686,0.0001247398,0.001353425,0.00007495496,0.0003471367,0.0003415676,0.001932419,0.0007481004,0.00215128,0.7026998],"study_design_scores_gemma":[0.0154201,0.002012238,0.2729654,0.00129225,0.001346423,0.000074281,0.0004582075,0.5921223,0.005027451,0.002568054,0.1059432,0.0007700759],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5228315,0.410218,0.01338746,0.04350122,0.0009489467,0.007052111,0.00002527319,0.0005785635,0.001456958],"genre_scores_gemma":[0.9854775,0.001986508,0.01071607,0.0006478801,0.0004750692,0.0002792915,0.0001343675,0.00007542862,0.0002078785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7019298,"threshold_uncertainty_score":0.9123273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04966042672850079,"score_gpt":0.4247021297416508,"score_spread":0.37504170301315,"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."}}