{"id":"W3205206067","doi":"10.1016/j.compbiomed.2021.104935","title":"Rethinking modeling Alzheimer's disease progression from a multi-task learning perspective with deep recurrent neural network","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Task (project management); Cognition; Machine learning; Missing data; Correlation; Time point; Neuroimaging; Flexibility (engineering); Perspective (graphical); Cognitive flexibility; Alzheimer's Disease Neuroimaging Initiative; Deep learning; Cognitive psychology; Psychology; Cognitive impairment; Neuroscience; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003046873,0.0001655418,0.0003392242,0.00008972853,0.0001488184,0.000009697944,0.00005755825,0.00007864573,0.00003430889],"category_scores_gemma":[0.0001548757,0.0001120506,0.00003136908,0.0002113227,0.0002601197,0.00004244279,0.0001301434,0.0005704652,0.000001147816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004332911,"about_ca_system_score_gemma":0.00008737964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005092632,"about_ca_topic_score_gemma":0.00003250001,"domain_scores_codex":[0.9985156,0.0002804858,0.000202474,0.0004958217,0.0001596138,0.0003459956],"domain_scores_gemma":[0.9992231,0.0001713152,0.00005462251,0.0001288992,0.0001912733,0.0002308024],"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":[0.001320436,0.0002162561,0.9161768,0.00003322184,0.0002372519,0.001001617,0.003079157,0.0006982917,0.0002192554,0.0003495901,0.00003628802,0.07663184],"study_design_scores_gemma":[0.00782272,0.001803399,0.2590131,0.002740241,0.000394911,0.00008016498,0.001721827,0.7224377,0.00002808799,0.003551936,0.0001727546,0.000233134],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.923182,0.03480633,0.0366892,0.004252457,0.0003484212,0.0004441811,0.000001440719,0.00005510449,0.0002208229],"genre_scores_gemma":[0.9911838,0.0008460941,0.006601614,0.0007460571,0.0004042946,0.00002624319,0.0001676322,0.00001234862,0.0000118975],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7217394,"threshold_uncertainty_score":0.4569291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0413925961030415,"score_gpt":0.3746770428201263,"score_spread":0.3332844467170848,"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."}}