{"id":"W4280505354","doi":"10.1038/s41593-022-01059-9","title":"Meta-matching as a simple framework to translate phenotypic predictive models from big to small data","year":2022,"lang":"en","type":"article","venue":"Nature Neuroscience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":98,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"National Institute on Drug Abuse; National Institute of Mental Health; National Institute on Aging; Medical Research Council","keywords":"Biobank; Human Connectome Project; Matching (statistics); Neuroimaging; Computer science; Scale (ratio); Connectome; Machine learning; Variance (accounting); Meta-analysis; Phenotype; Artificial intelligence; Exploit; Predictive modelling; Simple (philosophy); Data mining; Statistics; Bioinformatics; Neuroscience; Functional connectivity; Biology; Mathematics; Medicine","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":[0.01119778,0.001405414,0.001995369,0.00295374,0.0008409543,0.003261528,0.003381263,0.001703584,0.008668189],"category_scores_gemma":[0.05086876,0.001082115,0.003910462,0.002907159,0.0009618212,0.004170492,0.004434464,0.003631988,0.001897651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009851031,"about_ca_system_score_gemma":0.001817233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00221583,"about_ca_topic_score_gemma":0.004508192,"domain_scores_codex":[0.9965339,0.001919282,0.0002720489,0.000739528,0.0004366317,0.00009870205],"domain_scores_gemma":[0.9808195,0.01343,0.0006459394,0.00410002,0.0006796539,0.0003248559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007189556,0.0003245622,0.009361367,0.001015472,0.003811903,0.0007469826,0.0002681783,0.4686075,0.004442255,0.2264268,0.01695335,0.2673227],"study_design_scores_gemma":[0.00004735315,0.00004294765,0.0003686714,0.0000530659,0.0002249676,0.00009069726,0.00002892333,0.6297539,0.00107578,0.363849,0.004442302,0.00002231763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003614007,0.0003133241,0.9906165,0.0005057091,0.0001220845,0.00006100508,0.001253509,0.00261408,0.0008997924],"genre_scores_gemma":[0.2239894,0.000542284,0.7658032,0.0009228085,0.0002916045,0.0004579271,0.004235612,0.001837607,0.001919467],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01119778,"threshold_uncertainty_score":0.05922019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1663122275993087,"score_gpt":0.3256127642947977,"score_spread":0.1593005366954891,"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."}}