{"id":"W3107095885","doi":"10.1038/s41598-020-77220-w","title":"A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":291,"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; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Meso Scale Diagnostics; Medical Research Council; Eli Lilly and Company; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; National Health and Medical Research Council; Foundation for the National Institutes of Health","keywords":"Dementia; Feature selection; Computer science; Concordance; Machine learning; Artificial intelligence; Clinical trial; Cohort; Neuroimaging; Missing data; Disease; Data mining; Medicine; Psychiatry; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04415127,0.001598298,0.001665409,0.005782464,0.0007705913,0.002081664,0.00111051,0.001522661,0.0008409827],"category_scores_gemma":[0.07531134,0.0004390255,0.002573928,0.002653457,0.0007543679,0.00294389,0.001490435,0.002289009,0.0003621533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001739877,"about_ca_system_score_gemma":0.002022673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006177002,"about_ca_topic_score_gemma":0.004762698,"domain_scores_codex":[0.9850035,0.009786905,0.001313401,0.00136424,0.002209522,0.0003225091],"domain_scores_gemma":[0.8890275,0.09659201,0.002322283,0.004258321,0.006980385,0.0008194331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004097922,0.0007627265,0.09878667,0.0007446242,0.00381601,0.0001240258,0.0004735384,0.3720891,0.001416021,0.007550327,0.004559993,0.5055791],"study_design_scores_gemma":[0.0001130823,0.0008095682,0.02120246,0.0001807737,0.0002082082,0.0001026999,0.0001434148,0.9701474,0.0007102187,0.005067965,0.001230254,0.00008406924],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4321803,0.02160195,0.5333907,0.003276692,0.000938681,0.0007467025,0.001904851,0.001972077,0.003988171],"genre_scores_gemma":[0.7982067,0.005327099,0.1919464,0.0003580044,0.0002948888,0.0005520782,0.002113162,0.0002300889,0.0009715534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04415127,"threshold_uncertainty_score":0.233497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2089350912877315,"score_gpt":0.5174073043725682,"score_spread":0.3084722130848367,"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."}}