{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.00370721,0.0001527129,0.0001506684,0.0005448788,0.002025941,0.00006962805,0.0003419254,0.00002989135,0.0004877161],"category_scores_gemma":[0.008907672,0.0001428353,0.00006330039,0.001708659,0.0001262511,0.0002751844,0.0003268391,0.0004568,0.00003227176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004886365,"about_ca_system_score_gemma":0.00006005208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002253694,"about_ca_topic_score_gemma":0.00004354258,"domain_scores_codex":[0.9968458,0.0009417671,0.0003038989,0.000566448,0.001019894,0.0003221728],"domain_scores_gemma":[0.9946833,0.004779675,0.0001343865,0.0003318757,0.00004276507,0.00002798966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001019633,0.0004515794,0.03306991,0.0001138114,0.00004883123,0.00005813038,0.01858446,0.05628929,0.7516658,0.007381068,0.09488231,0.03735287],"study_design_scores_gemma":[0.001619514,0.000336256,0.7949747,0.00004411266,0.00001773526,0.00006489331,0.00270209,0.05856441,0.001367384,0.003622845,0.1362914,0.0003945534],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9759273,0.00009537891,0.0001868182,0.01401413,0.0005462113,0.0008037324,0.00001341261,0.000069118,0.008343901],"genre_scores_gemma":[0.9916036,0.000003372465,0.00001781583,0.005918289,0.0001713525,0.0004512364,0.00001112436,0.00001824536,0.001804966],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7619048,"threshold_uncertainty_score":0.9994407,"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."}}