{"id":"W4385989015","doi":"10.1016/j.artmed.2023.102636","title":"Deep grading for MRI-based differential diagnosis of Alzheimer’s disease and Frontotemporal dementia","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; University of California, San Francisco; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Centre National de la Recherche Scientifique; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Agence Nationale de la Recherche; 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; National Institute on Aging; Alzheimer's Association","keywords":"Frontotemporal dementia; Dementia; Differential diagnosis; Disease; Alzheimer's disease; Grading (engineering); Computer science; Medicine; Neuroscience; Artificial intelligence; Pathology; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001895293,0.0009322615,0.0007536027,0.003930817,0.0006939172,0.001523094,0.001113977,0.0008041775,0.003411182],"category_scores_gemma":[0.005040273,0.0002889159,0.0006894052,0.001215728,0.0005488168,0.001463309,0.001696918,0.0009610755,0.0009671486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007997616,"about_ca_system_score_gemma":0.001300648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004799773,"about_ca_topic_score_gemma":0.01220084,"domain_scores_codex":[0.9994568,0.00008871414,0.0001163034,0.00007574652,0.0001366979,0.0001257178],"domain_scores_gemma":[0.998457,0.0002155092,0.0002698187,0.0001599191,0.0006565125,0.0002412806],"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":[0.00362404,0.0004232863,0.4184631,0.001597916,0.0006616407,0.002781508,0.000928444,0.002194354,0.03581426,0.00390168,0.01484128,0.5147684],"study_design_scores_gemma":[0.0005705438,0.002483456,0.83417,0.002300848,0.001842729,0.01796672,0.002850136,0.04122936,0.02693042,0.03063712,0.03873124,0.0002874428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.89788,0.01306562,0.05360294,0.001361623,0.0007110578,0.001353315,0.004719939,0.0006137867,0.02669185],"genre_scores_gemma":[0.9501789,0.002554647,0.04093998,0.0003019604,0.0001449516,0.0003379849,0.002267214,0.00006749944,0.003206775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004799773,"threshold_uncertainty_score":0.01141149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1042675318891038,"score_gpt":0.3956946516652534,"score_spread":0.2914271197761497,"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."}}