{"id":"W4319216497","doi":"10.1016/j.neuroscience.2023.01.029","title":"Comparison of Machine Learning-based Approaches to Predict the Conversion to Alzheimer’s Disease from Mild Cognitive Impairment","year":2023,"lang":"en","type":"article","venue":"Neuroscience","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Università degli Studi G. d'Annunzio Chieti - Pescara; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; European Commission; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Cognitive impairment; Alzheimer's disease; Disease; Psychology; Cognition; Neuroscience; Artificial intelligence; Machine learning; Cognitive psychology; Computer science; Medicine; 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":[0.0108947,0.001563405,0.001453362,0.003780388,0.0003505963,0.001504921,0.0009122168,0.001533284,0.0005328729],"category_scores_gemma":[0.01266962,0.0002815177,0.001384188,0.001130696,0.0003615885,0.001186192,0.0008697693,0.001011371,0.0003334154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000736418,"about_ca_system_score_gemma":0.001000771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002943403,"about_ca_topic_score_gemma":0.001981847,"domain_scores_codex":[0.9963691,0.00172942,0.0003987821,0.0004594365,0.000800287,0.0002429546],"domain_scores_gemma":[0.9927675,0.004924961,0.0003210492,0.0002741254,0.001480716,0.0002316839],"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":[0.006469184,0.001449232,0.1446312,0.0008959906,0.004284286,0.0001446871,0.0002638854,0.2456173,0.00259474,0.001607952,0.003028522,0.589013],"study_design_scores_gemma":[0.0001550675,0.002116765,0.05639075,0.000196186,0.0008051998,0.0001321246,0.000199318,0.9339944,0.002588509,0.002027729,0.001316461,0.00007745315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8768354,0.01851842,0.09446955,0.001116434,0.0006835755,0.000417075,0.0008732911,0.0009255959,0.006160611],"genre_scores_gemma":[0.9656969,0.002307546,0.02985361,0.0001904518,0.0001613763,0.0001367517,0.0009796992,0.00005096275,0.0006227302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0108947,"threshold_uncertainty_score":0.05761737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.165921790424517,"score_gpt":0.3678839720235804,"score_spread":0.2019621815990634,"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."}}