{"id":"W4220800641","doi":"10.1002/hbm.25837","title":"Mind the gap: Performance metric evaluation in brain‐age prediction","year":2022,"lang":"en","type":"article","venue":"Human Brain Mapping","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":167,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"H2020 European Research Council; Medical Research Council; Helse Sør-Øst RHF; Medical Research Council Canada; Fondation Leenaards; Agence Nationale de la Recherche; Horizon 2020 Framework Programme; Norges Forskningsråd; National Institute on Aging; Deutsche Forschungsgemeinschaft; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Mean squared error; Statistics; Metric (unit); Pearson product-moment correlation coefficient; Sample size determination; Range (aeronautics); Variance (accounting); Correlation; Mathematics; Correlation coefficient; Explained variation; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03119241,0.001880322,0.001434011,0.003829463,0.0005535373,0.002174235,0.001641546,0.001751591,0.001326948],"category_scores_gemma":[0.1070083,0.0003141,0.001190625,0.002525538,0.0007587286,0.001949008,0.002185839,0.001212683,0.0004895346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00122471,"about_ca_system_score_gemma":0.001805166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0081777,"about_ca_topic_score_gemma":0.004173113,"domain_scores_codex":[0.9853753,0.00831067,0.001515487,0.001743417,0.002642001,0.0004130996],"domain_scores_gemma":[0.9238945,0.05629398,0.004464173,0.004605198,0.009798896,0.0009432803],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004804726,0.0007741116,0.2258894,0.001772839,0.003664947,0.00039394,0.0009010559,0.3718993,0.005115421,0.006466675,0.02306764,0.35525],"study_design_scores_gemma":[0.0001311856,0.001408971,0.03932642,0.0002491781,0.0003364654,0.0003272247,0.0002787811,0.9419248,0.005678049,0.006497253,0.003732128,0.0001094276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6022658,0.01613473,0.3567691,0.001547851,0.0007937147,0.0006214462,0.00768032,0.008601099,0.005585999],"genre_scores_gemma":[0.9062911,0.0006018129,0.08617172,0.00019278,0.00007634421,0.0003815496,0.005322234,0.0003884388,0.0005738871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9688076,"threshold_uncertainty_score":0.1649632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1348613797827382,"score_gpt":0.3060718656202675,"score_spread":0.1712104858375293,"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."}}