{"id":"W3027945570","doi":"10.1038/s41398-020-0831-9","title":"Improved metabolomic data-based prediction of depressive symptoms using nonlinear machine learning with feature selection","year":2020,"lang":"en","type":"article","venue":"Translational Psychiatry","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Aging","funders":"Ministry of Education, Culture, Sports, Science and Technology; Japan Agency for Medical Research and Development","keywords":"Feature selection; Lasso (programming language); Artificial intelligence; Random forest; Machine learning; Population; Support vector machine; Predictive modelling; Computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008525488,0.0001589492,0.0001934004,0.00004636506,0.0001051884,0.00001026252,0.0001448028,0.0001029678,0.00001756311],"category_scores_gemma":[0.00002076897,0.0001355197,0.00006351581,0.0001979976,0.00004639383,0.00001150736,0.00002508385,0.0001760071,3.945962e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003626769,"about_ca_system_score_gemma":0.0001649955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001483635,"about_ca_topic_score_gemma":0.00004536014,"domain_scores_codex":[0.9990831,0.0000476813,0.0001930264,0.0003886039,0.0001518194,0.0001357823],"domain_scores_gemma":[0.9995259,0.00000923646,0.0001528063,0.0001638597,0.00009305547,0.00005515909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001168945,0.000105659,0.1569813,0.00007441029,0.0005996465,2.285829e-7,0.00003255332,0.02033775,0.8199047,0.0001247704,0.0001803415,0.0004897436],"study_design_scores_gemma":[0.005117609,0.001291253,0.03922934,0.0000356631,0.0007067996,0.0000157486,0.00004639614,0.8600626,0.08194657,0.00004727671,0.01103484,0.0004658864],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8677693,0.005308331,0.12352,0.001742927,0.000207953,0.0003327209,0.0009823138,0.00003675612,0.00009972091],"genre_scores_gemma":[0.9409624,0.000060787,0.05640879,0.0001848103,0.0004576972,0.00000476937,0.001875171,0.00002713353,0.00001842849],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8397248,"threshold_uncertainty_score":0.5526333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0184073327465981,"score_gpt":0.2513387721123791,"score_spread":0.232931439365781,"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."}}