{"id":"W4390649631","doi":"10.1101/2023.12.31.573801","title":"Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"","keywords":"Matching (statistics); Biobank; Human Connectome Project; Computer science; Transfer of learning; Artificial intelligence; Variance (accounting); Meta-analysis; Meta learning (computer science); Machine learning; Deep learning; Convolutional neural network; Pattern recognition (psychology); Statistics; Mathematics; Functional connectivity; Psychology; Bioinformatics","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":[0.005112237,0.001978475,0.001692998,0.00180972,0.0005313065,0.001708952,0.002486443,0.001496958,0.002252522],"category_scores_gemma":[0.01310887,0.0007283166,0.00327478,0.001632473,0.0007549587,0.003069053,0.001961967,0.002447714,0.001166539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035713,"about_ca_system_score_gemma":0.00121249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004057109,"about_ca_topic_score_gemma":0.00575896,"domain_scores_codex":[0.9985453,0.000521905,0.00008566304,0.000628724,0.0001365498,0.00008182332],"domain_scores_gemma":[0.9958507,0.002314308,0.000260104,0.001104186,0.0003405111,0.0001302154],"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":[0.0008096348,0.0004902789,0.04189615,0.000427942,0.002389114,0.0005736434,0.0002371692,0.7127758,0.007193025,0.004961713,0.008092914,0.2201526],"study_design_scores_gemma":[0.00004393581,0.0001180496,0.003348988,0.0000417504,0.0002537307,0.0001046248,0.00005642147,0.9673446,0.002154552,0.02492188,0.001574424,0.00003709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.17034,0.00246017,0.809512,0.002405756,0.0003060706,0.0001789028,0.004440455,0.008338226,0.002018464],"genre_scores_gemma":[0.811604,0.0007528663,0.1719448,0.001449974,0.0001885589,0.0003581975,0.01106095,0.0008640232,0.001776606],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005112237,"threshold_uncertainty_score":0.02703637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1460104573416356,"score_gpt":0.2756619219471683,"score_spread":0.1296514646055327,"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."}}