{"id":"W4223442957","doi":"10.1038/s41746-022-00577-x","title":"A high-generalizability machine learning framework for predicting the progression of Alzheimer’s disease using limited data","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Program on Open Innovation Platform with Enterprises, Research Institute and Academia; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Eisai; Japan Science and Technology Agency; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Fujifilm Corporation; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Generalizability theory; Artificial intelligence; Machine learning; Computer science; Disease; Alzheimer's disease; Psychology; Medicine; Developmental 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005089375,0.001515283,0.001317933,0.002149213,0.0005111246,0.001134319,0.002323543,0.001766539,0.001210313],"category_scores_gemma":[0.008362229,0.0004761193,0.001476335,0.001332815,0.0007203834,0.001544862,0.001605102,0.002558304,0.0008076672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008223829,"about_ca_system_score_gemma":0.001228423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01221869,"about_ca_topic_score_gemma":0.01190769,"domain_scores_codex":[0.99831,0.0006337911,0.0001057308,0.0005214348,0.0003135262,0.0001155501],"domain_scores_gemma":[0.9967512,0.001897651,0.0002881984,0.0003226487,0.0006165383,0.0001238578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004317668,0.0006751322,0.01456296,0.0002008233,0.0005057628,0.0004809979,0.0002120045,0.5998226,0.003928293,0.005315035,0.006488189,0.3673764],"study_design_scores_gemma":[0.00001628196,0.00007134317,0.001005701,0.00001597821,0.0000304085,0.00003799182,0.00001038901,0.9939957,0.0002944117,0.003984335,0.0005269508,0.00001048429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05039307,0.001687768,0.942125,0.001190182,0.0001022577,0.0002630162,0.000736759,0.002171778,0.001330281],"genre_scores_gemma":[0.781185,0.001246671,0.2086406,0.0009924171,0.0004790323,0.0006456723,0.002948696,0.0001636844,0.003698224],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01221869,"threshold_uncertainty_score":0.02691549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3684775004553096,"score_gpt":0.5231412404781808,"score_spread":0.1546637400228711,"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."}}