{"id":"W2898277231","doi":"10.1101/244574","title":"Data-driven approaches for Tau-PET imaging biomarkers in Alzheimer’s disease","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal; McGill University; Montreal Neurological Institute and Hospital","funders":"BrightFocus Foundation; Skånes universitetssjukhus; Marcus och Amalia Wallenbergs minnesfond; Lunds Universitet; Vetenskapsrådet; Australian Government","keywords":"Positron emission tomography; Dementia; Neuroimaging; Cognition; Demographics; Cluster analysis; Alzheimer's disease; Psychology; Pattern recognition (psychology); Pathology; Nuclear medicine; Medicine; Artificial intelligence; Disease; Neuroscience; Computer science; Cognitive psychology","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":[0.01737174,0.001849765,0.002045939,0.003620481,0.000945892,0.001869719,0.003718821,0.001728129,0.001319096],"category_scores_gemma":[0.03431761,0.001040179,0.004588235,0.002294326,0.001156536,0.0009881778,0.002550456,0.002543072,0.000704105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001776579,"about_ca_system_score_gemma":0.002668836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005919054,"about_ca_topic_score_gemma":0.006148357,"domain_scores_codex":[0.9920481,0.005017738,0.0004620242,0.001390488,0.0008807782,0.0002008072],"domain_scores_gemma":[0.9833575,0.01188741,0.0007724801,0.001440866,0.002291584,0.0002500085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.002075161,0.001142627,0.05671781,0.001038065,0.004547611,0.0009744219,0.001360579,0.5449084,0.02171727,0.02009333,0.005621369,0.3398035],"study_design_scores_gemma":[0.0000740214,0.00012998,0.005288159,0.00003025839,0.0001130104,0.00007951605,0.0001003298,0.9728215,0.002822131,0.01695851,0.001530557,0.00005196065],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02800985,0.0002257445,0.9690133,0.0002749185,0.00003547182,0.0004489626,0.0006487274,0.001141361,0.0002016823],"genre_scores_gemma":[0.2715738,0.0001291676,0.7215143,0.0001881628,0.00006320187,0.001867245,0.003570833,0.0004693955,0.0006239503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01737174,"threshold_uncertainty_score":0.09187168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0683331630211551,"score_gpt":0.308818525319882,"score_spread":0.2404853622987269,"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."}}