{"id":"W3207397300","doi":"10.1093/gigascience/giab071","title":"Population modeling with machine learning can enhance measures of mental health","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"Medical Research Council; Canadian Institutes of Health Research; Canada First Research Excellence Fund","keywords":"Biobank; Machine learning; Artificial intelligence; Population; Mental health; Computer science; Psychology; Clinical psychology; Cognitive psychology; Medicine; Psychiatry; Bioinformatics; Environmental health","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003465356,0.00009194316,0.0001557494,0.0000545241,0.0004853717,0.00002605601,0.0001269386,0.00001336259,0.00000867728],"category_scores_gemma":[0.002332337,0.00007990179,0.00002666537,0.0005681956,0.000113662,0.0001886749,0.00008179314,0.0001254205,0.000002058913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008494887,"about_ca_system_score_gemma":0.0001610766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005698916,"about_ca_topic_score_gemma":0.001222426,"domain_scores_codex":[0.9984533,0.0001348602,0.0001592929,0.0004465418,0.0005815809,0.0002244733],"domain_scores_gemma":[0.999338,0.0002728941,0.0001055829,0.0001486873,0.00008015716,0.00005466985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007902183,0.0001480148,0.02949564,0.00006372912,0.000009525912,0.00001218975,0.003288472,0.1581924,0.7892427,0.005342388,0.00008318618,0.01404274],"study_design_scores_gemma":[0.0005761571,0.0005720496,0.01027895,0.0002330727,0.000007334354,0.0001347472,0.0008546542,0.3463797,0.6386621,0.001196412,0.0006765077,0.0004283412],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700192,0.000320975,0.02073065,0.008116919,0.0001933208,0.0001289627,0.0000154369,0.00006376388,0.0004107906],"genre_scores_gemma":[0.9974048,0.00005816585,0.001271562,0.001055989,0.00001624669,0.000005252838,0.000002980971,0.000007344743,0.0001777152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1881873,"threshold_uncertainty_score":0.3733136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05909974512401339,"score_gpt":0.2878850603960947,"score_spread":0.2287853152720813,"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."}}