{"id":"W4389462004","doi":"10.1101/2023.12.05.569848","title":"Multilayer meta-matching: translating phenotypic prediction models from multiple datasets to small data","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"National Medical Research Council; Medical Research Council; National Institutes of Health; Temasek Foundation","keywords":"Matching (statistics); Computer science; Biobank; Meta-analysis; Artificial intelligence; Machine learning; Human Connectome Project; Sample size determination; Meta learning (computer science); Transfer of learning; Sample (material); Pattern recognition (psychology); Data mining; Statistics; Bioinformatics; Mathematics; Functional connectivity; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009806025,0.002467575,0.001900928,0.00184346,0.0006281446,0.001605225,0.003297916,0.001737387,0.002470939],"category_scores_gemma":[0.02459912,0.0008656597,0.003972679,0.001879519,0.0006831589,0.00344654,0.003709686,0.003044921,0.001309795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008397519,"about_ca_system_score_gemma":0.001288052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004070138,"about_ca_topic_score_gemma":0.005682595,"domain_scores_codex":[0.9964359,0.001687448,0.0002357096,0.001219835,0.0002750219,0.0001461717],"domain_scores_gemma":[0.9934064,0.003373702,0.0004488935,0.002089227,0.0005156415,0.0001661179],"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":[0.001606264,0.0009956976,0.06133198,0.0009342845,0.005332714,0.0006921424,0.0004769204,0.408472,0.0187254,0.005874809,0.01414636,0.4814115],"study_design_scores_gemma":[0.0001147142,0.0003269861,0.006051162,0.00006374628,0.0004951222,0.0001438527,0.00008720706,0.9625375,0.005301203,0.0221489,0.002663222,0.0000663609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1019444,0.001978345,0.8794109,0.001503218,0.000298645,0.0002939143,0.003266734,0.009981474,0.001322402],"genre_scores_gemma":[0.6697444,0.0006937596,0.3148723,0.001504222,0.0002224471,0.0007544977,0.009606306,0.000976711,0.001625478],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009806025,"threshold_uncertainty_score":0.0518598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2116873727345144,"score_gpt":0.2803734322502938,"score_spread":0.06868605951577941,"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."}}