{"id":"W2509318466","doi":"10.18653/v1/w16-0302","title":"Towards Early Dementia Detection: Fusing Linguistic and Non-Linguistic Clinical Data","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Synarc; University of Southern California; Medpace; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Alzheimer's Drug Discovery Foundation; Foundation for the National Institutes of Health","keywords":"Computer science; Dementia; Linguistics; Natural language processing; Linguistic analysis; Artificial intelligence; Deep linguistic processing; Medicine; Disease; Philosophy","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008134495,0.0001196774,0.0001650576,0.00005495522,0.0001238585,0.0001840251,0.0009756522,0.00006867648,0.00002326689],"category_scores_gemma":[0.001194158,0.00008421788,0.00002961523,0.0001069901,0.00006159572,0.0002390932,0.00121251,0.0001051206,0.00004986203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001658195,"about_ca_system_score_gemma":0.00008466138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001494485,"about_ca_topic_score_gemma":0.00005669247,"domain_scores_codex":[0.9983772,0.00005241575,0.0004061253,0.0006939485,0.0002131889,0.0002571366],"domain_scores_gemma":[0.9981652,0.0002092777,0.00007971776,0.001292333,0.0001136596,0.0001397781],"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":[0.000007332939,0.00003788594,0.0120256,0.00001756007,0.00005701136,0.0000411507,0.0002579082,0.000003143318,0.0003271248,0.007768125,0.00007191774,0.9793853],"study_design_scores_gemma":[0.002154996,0.0003312966,0.06824912,0.0002228434,0.0001380703,0.00007507455,0.00001380063,0.8777613,0.0009266452,0.02312458,0.0261101,0.0008921861],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03619598,0.0001235524,0.9580572,0.0002918428,0.001689551,0.00008419206,0.000001871399,0.0001496043,0.003406195],"genre_scores_gemma":[0.8702813,0.00002827906,0.1286954,0.0001569546,0.0006848208,0.00000176565,4.730604e-7,0.000007555508,0.0001434614],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.978493,"threshold_uncertainty_score":0.3434305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09277553604152745,"score_gpt":0.3442513983840846,"score_spread":0.2514758623425572,"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."}}