{"id":"W2775151852","doi":"10.1109/smc.2017.8123168","title":"Feature abstraction for early detection of multi-type of dementia with sparse auto-encoder","year":2017,"lang":"en","type":"article","venue":"","topic":"Traditional Chinese Medicine Studies","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Computer science; Dementia; Artificial intelligence; Linear discriminant analysis; Pattern recognition (psychology); Feature extraction; Machine learning; Abstraction; Feature (linguistics); Curse of dimensionality; Dimensionality reduction; Key (lock); Logistic regression; Data mining; Deep learning; Medicine","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":[0.00008516162,0.00009249432,0.0002297857,0.00006324062,0.00009347903,0.000004530109,0.00004742829,0.00004883818,0.00002184618],"category_scores_gemma":[0.000205093,0.00005937744,0.00005025522,0.00003927693,0.0001196954,0.0001093584,0.00001019637,0.00008726754,0.000001989058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001600415,"about_ca_system_score_gemma":0.00003043199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001596486,"about_ca_topic_score_gemma":0.0003312227,"domain_scores_codex":[0.9994503,0.000004779278,0.0001331366,0.000127551,0.0001952078,0.00008900472],"domain_scores_gemma":[0.9991218,0.00004532242,0.0002092947,0.0002250929,0.0003606607,0.00003776165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.003084813,0.0007429222,0.3068697,0.0008336337,0.001293057,0.000009935275,0.0005531439,0.00003244804,0.6765988,0.0002212352,0.001990583,0.00776973],"study_design_scores_gemma":[0.002464372,0.001314586,0.9320008,0.0001130209,0.0003193895,0.00001772157,0.0001035957,0.0002651317,0.0628002,0.00003888099,0.0005076816,0.00005465646],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987675,0.0001358603,0.008621062,0.00102275,0.0002628034,0.0004761346,0.00001098336,0.00002905868,0.001766338],"genre_scores_gemma":[0.9908789,0.00001128682,0.007779539,0.00002384341,0.000132731,0.00001507137,0.000009797918,0.0000122339,0.001136639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6251311,"threshold_uncertainty_score":0.2421342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06010942020019165,"score_gpt":0.3300688283532084,"score_spread":0.2699594081530168,"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."}}