{"id":"W2801297078","doi":"10.1016/j.cmpb.2018.04.028","title":"Generalized fused group lasso regularized multi-task feature learning for predicting cognitive outcomes in Alzheimers disease","year":2018,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Discriminative model; Artificial intelligence; Computer science; Neuroimaging; Multi-task learning; Alzheimer's Disease Neuroimaging Initiative; Machine learning; Regularization (linguistics); Correlation; Cognition; Pattern recognition (psychology); Task (project management); Psychology; Mathematics; Cognitive impairment","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":[0.002730507,0.0003104462,0.0007314634,0.0005092789,0.0001405368,0.00006078378,0.0001120884,0.000151174,0.00002227035],"category_scores_gemma":[0.0005077712,0.0002321365,0.0001260747,0.0006589412,0.0005021246,0.0000958747,0.0001586235,0.0004300866,0.000001410358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004612899,"about_ca_system_score_gemma":0.00006308748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005106726,"about_ca_topic_score_gemma":0.00002172194,"domain_scores_codex":[0.9972121,0.0006697289,0.000456608,0.0006740938,0.000333099,0.0006544406],"domain_scores_gemma":[0.9984838,0.0005741318,0.0001284033,0.0001790561,0.0002512668,0.0003832914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001254431,0.0004787101,0.5183604,0.0001672768,0.00019827,0.00006255597,0.000708009,1.237551e-7,0.001565809,0.00001963501,0.00003481782,0.47715],"study_design_scores_gemma":[0.03558623,0.004771917,0.8754787,0.00132604,0.0004378723,0.00002229164,0.0006911963,0.07424814,0.0003516557,0.0002353514,0.006492907,0.0003577288],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.703392,0.001307821,0.2898668,0.001844737,0.0003823857,0.00305245,0.000009356668,0.0001094601,0.00003499893],"genre_scores_gemma":[0.4676717,0.0001237649,0.5296545,0.0006733497,0.0004959285,0.0006211197,0.0003544907,0.00004510511,0.0003600108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4767922,"threshold_uncertainty_score":0.9466254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0693732139309282,"score_gpt":0.4215476210739119,"score_spread":0.3521744071429837,"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."}}