{"id":"W1992054897","doi":"10.1371/journal.pone.0033182","title":"Predicting Future Clinical Changes of MCI Patients Using Longitudinal and Multimodal Biomarkers","year":2012,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":296,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Mental Health; National Institute on Aging; National Key Research and Development Program of China; 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; Servier; National Natural Science Foundation of China; Eisai; Genentech; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Synarc; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Foundation for the National Institutes of Health; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Science Foundation","keywords":"Time point; Neuroimaging; Feature selection; Longitudinal study; Artificial intelligence; Computer science; Clinical trial; Support vector machine; Cognition; Regression; Pattern recognition (psychology); Medicine; Internal medicine; Mathematics; Statistics; Pathology","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":[0.0005779738,0.0001028884,0.0002244086,0.00007624357,0.000100244,0.00002043521,0.0002408137,0.00009762494,0.000006479962],"category_scores_gemma":[0.0002960181,0.00009583091,0.00002841538,0.0001655605,0.00005436166,0.0002457156,0.0002854213,0.0002310985,0.000002313452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002287591,"about_ca_system_score_gemma":0.00002275699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001360156,"about_ca_topic_score_gemma":0.00001572526,"domain_scores_codex":[0.9986536,0.0001841489,0.0002748414,0.0002492282,0.0003443635,0.0002938034],"domain_scores_gemma":[0.9990333,0.0001819842,0.0002102034,0.0002850933,0.0001220783,0.0001672887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000101885,0.0004183034,0.9886088,0.0001566729,0.00006102693,5.568708e-7,0.0006101453,0.000001821078,0.0001161703,0.00006297453,0.000005138597,0.009948213],"study_design_scores_gemma":[0.0003173928,0.0001687911,0.9129591,0.0001411295,0.00002742753,0.000001565842,0.00002878916,0.08600639,0.0002353973,0.000008116253,0.00001263441,0.00009328837],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974717,0.000378216,0.001037351,0.000491386,0.0003251876,0.0001823133,0.000005348066,0.00006466315,0.00004384406],"genre_scores_gemma":[0.9209354,0.00002460177,0.07845256,0.00006053775,0.0005076419,0.000003282845,0.000002551785,0.000009270087,0.00000418006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08600456,"threshold_uncertainty_score":0.3907871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1072909395699575,"score_gpt":0.3356520740830305,"score_spread":0.2283611345130731,"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."}}