{"id":"W7118459977","doi":"10.1002/alz70856_106868","title":"A Machine Learning‐Based MRI Marker Predicts Incident Hypertension and Mediates the Relationship Between Hypertension and Cognition","year":2025,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Cognition; Neuroimaging; Magnetic resonance imaging; Longitudinal study; Proportional hazards model; Mediation; White matter; Correlation; Cognitive test","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001255281,0.0004784078,0.0003834559,0.0006546929,0.0002405192,0.0006668488,0.0003116597,0.0003938011,0.001627063],"category_scores_gemma":[0.003979283,0.0002085637,0.0005397417,0.000602357,0.0002598508,0.0004008842,0.0004273847,0.0004408453,0.0001847018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002097135,"about_ca_system_score_gemma":0.0003647778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003998809,"about_ca_topic_score_gemma":0.004541955,"domain_scores_codex":[0.9996208,0.0001502676,0.00003367485,0.0001044016,0.00004522505,0.00004556324],"domain_scores_gemma":[0.9976802,0.001035472,0.0006459112,0.0002740457,0.0001789886,0.000185331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002327658,0.00004403721,0.9935663,0.00002220035,0.0003685963,0.00004141033,0.0000424869,0.0006997831,0.0009159439,0.00005694079,0.00008967668,0.003919701],"study_design_scores_gemma":[0.000008721781,0.0001200336,0.9862884,0.00001771366,0.0001997366,0.0001421879,0.00005525162,0.01200282,0.0005432551,0.0004622162,0.0001530539,0.000006582579],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969631,0.0003773609,0.001688749,0.00008432211,0.00000836997,0.000006738371,0.0004187886,0.00002366175,0.000429078],"genre_scores_gemma":[0.9992519,0.00006345999,0.0004239986,0.00001103378,0.000009051663,0.000003484649,0.000169248,0.000001937369,0.00006591908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003998809,"threshold_uncertainty_score":0.007951081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04213010845937788,"score_gpt":0.2971576978729853,"score_spread":0.2550275894136074,"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."}}