{"id":"W3048423955","doi":"10.1101/2020.08.10.245373","title":"Meta-matching: a simple framework to translate phenotypic predictive models from big to small data","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"National Institutes of Health; National Supercomputing Centre Singapore; Canada First Research Excellence Fund; Centre d'Imagerie BioMédicale; National Research Foundation; Canadian Institute for Advanced Research; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital; Nvidia; National Research Foundation Singapore; Massachusetts General Hospital","keywords":"Matching (statistics); Biobank; Computer science; Scale (ratio); Meta-analysis; Phenotype; Population; Machine learning; Sample size determination; Neuroimaging; Artificial intelligence; Human Connectome Project; Predictive modelling; Exploit; Data mining; Statistics; Bioinformatics; Psychology; Biology; Functional connectivity; Medicine; Mathematics; Neuroscience; Cartography; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.07265384,0.003620968,0.005250372,0.01092008,0.001588583,0.005685365,0.005729122,0.003367153,0.005783237],"category_scores_gemma":[0.1723836,0.002140044,0.011736,0.008847781,0.001880264,0.004049162,0.006793274,0.005213837,0.001141339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001978587,"about_ca_system_score_gemma":0.005040369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006056956,"about_ca_topic_score_gemma":0.007490419,"domain_scores_codex":[0.9644684,0.02804381,0.001803001,0.003733824,0.001642393,0.0003086766],"domain_scores_gemma":[0.8729365,0.1084317,0.0044975,0.01024645,0.002717498,0.001170435],"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":[0.002223253,0.0005559678,0.03350037,0.005718535,0.03274705,0.001842232,0.0007853566,0.5536063,0.002694997,0.07371494,0.01660101,0.27601],"study_design_scores_gemma":[0.0003057104,0.0002646307,0.00206386,0.0004178882,0.003228293,0.0002267077,0.00007746811,0.7500667,0.000829716,0.2346608,0.007740161,0.0001180813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004966402,0.002837394,0.9849706,0.001461086,0.000181987,0.0003515021,0.002040189,0.002639815,0.0005511771],"genre_scores_gemma":[0.1971609,0.001580663,0.791888,0.001668888,0.0005222021,0.001602737,0.004137649,0.0008823447,0.0005566744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07265384,"threshold_uncertainty_score":0.3842348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1763285030830639,"score_gpt":0.280014740150422,"score_spread":0.1036862370673582,"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."}}