{"id":"W1978763244","doi":"10.1016/j.nicl.2013.05.004","title":"Accurate multimodal probabilistic prediction of conversion to Alzheimer's disease in patients with mild cognitive impairment","year":2013,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":254,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Engineering and Physical Sciences Research Council; University of California, San Diego; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; National Institutes of Health; Genentech; Takeda Pharmaceutical Company; IXICO; Servier; Eisai; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; Pfizer; Biogen; BioClinica; Synarc; Medpace; Novartis Pharmaceuticals Corporation; Eli Lilly and Company; Bristol-Myers Squibb; F. Hoffmann-La Roche; Merck; Alzheimer's Drug Discovery Foundation; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Artificial intelligence; Support vector machine; Machine learning; Probabilistic logic; Computer science; Population; Categorical variable; Probabilistic classification; Cognitive impairment; Disease; Naive Bayes classifier; Medicine; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003466715,0.0001550157,0.0002473458,0.0001017654,0.00004833769,0.00004127046,0.0003881663,0.00005846057,0.00003188863],"category_scores_gemma":[0.0009429048,0.0001276441,0.00006026846,0.0002901748,0.0001011784,0.0003613048,0.0002926387,0.0003837351,0.00008697507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002747872,"about_ca_system_score_gemma":0.0001215377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001759805,"about_ca_topic_score_gemma":0.000003997429,"domain_scores_codex":[0.9975551,0.0005068399,0.0006199026,0.0006513345,0.0003928645,0.0002739262],"domain_scores_gemma":[0.9979147,0.0006769107,0.0002009585,0.000468821,0.0003631017,0.0003755387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002980063,0.000612033,0.994808,0.00004158806,0.000008197019,0.000009894259,0.000136444,0.0005620256,7.282187e-7,0.0000145787,0.0001614837,0.003347027],"study_design_scores_gemma":[0.001744181,0.001636408,0.8675573,0.00009774543,0.00001551925,2.418639e-7,0.000004866897,0.1288032,0.000003842587,0.00003081112,0.00001409643,0.00009171799],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993543,0.000007806399,0.003079501,0.001077654,0.0003220304,0.001833833,0.00003222856,0.00007860558,0.00002530644],"genre_scores_gemma":[0.9962434,0.000001889195,0.002896785,0.0007092275,0.00003547129,0.00007382527,0.00001924423,0.00001361467,0.000006508545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1282412,"threshold_uncertainty_score":0.5205177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04313441181511563,"score_gpt":0.3352258579015511,"score_spread":0.2920914460864355,"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."}}