{"id":"W4409383178","doi":"10.1101/2025.04.09.25325520","title":"Predicting Future Brain Atrophy Based on Longitudinal MRI","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":0,"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; Commonwealth Scientific and Industrial Research Organisation; 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; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Atrophy; Neuroscience; Medicine; Physical medicine and rehabilitation; Psychology; Pathology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003743214,0.0003254511,0.0002691807,0.0003095739,0.0002688261,0.0001356787,0.0005946468,0.0003024169,0.0001792772],"category_scores_gemma":[0.0008933879,0.0003124783,0.0002198015,0.0004476676,0.00009405395,0.00004779585,0.0002159807,0.00123856,0.00008520312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001327665,"about_ca_system_score_gemma":0.0001837767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001207371,"about_ca_topic_score_gemma":0.00001471482,"domain_scores_codex":[0.9973013,0.0003799947,0.0003494309,0.001133242,0.0005348065,0.000301163],"domain_scores_gemma":[0.9981782,0.0004466953,0.0002663023,0.0009416018,0.00005638438,0.0001108508],"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":[0.001940868,0.002071726,0.5626698,0.003524648,0.0001290509,0.0006551737,0.001380138,0.08481536,0.2079168,0.02453835,0.04435142,0.06600666],"study_design_scores_gemma":[0.001409468,0.0002818217,0.3114932,0.0007610889,0.00007823268,0.00002381606,0.0001020132,0.4874705,0.1125053,0.001678132,0.08300801,0.001188466],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8377931,0.0000816096,0.0303218,0.05962376,0.01658276,0.001649998,0.0002905735,0.001758548,0.05189783],"genre_scores_gemma":[0.9923165,0.00001732096,0.0001434075,0.003563171,0.0009769968,0.0001255728,0.0000138946,0.00002757644,0.002815571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4026551,"threshold_uncertainty_score":0.9999327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03425632368688262,"score_gpt":0.282592085000299,"score_spread":0.2483357613134164,"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."}}