{"id":"W2926974277","doi":"10.30773/pi.2018.12.21.2","title":"Review of Machine Learning Algorithms for Diagnosing Mental Illness","year":2019,"lang":"en","type":"article","venue":"Psychiatry Investigation","topic":"Mental Health via Writing","field":"Psychology","cited_by":237,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Ministry of Science and Technology; National Research Foundation","keywords":"Naive Bayes classifier; Machine learning; Algorithm; Support vector machine; Artificial intelligence; Computer science; Random forest; Mental health; Big data; Gradient boosting; Data mining; Medicine; Psychiatry","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":[0.0007552675,0.0001451649,0.0002664267,0.00007951455,0.0001329032,0.000008317044,0.0001274692,0.00008097095,0.0006488336],"category_scores_gemma":[0.00008386038,0.0001516858,0.00008722553,0.0002211475,0.00004887281,0.0001187993,0.00002429057,0.00018778,0.0001474148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000056171,"about_ca_system_score_gemma":0.000055738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001213249,"about_ca_topic_score_gemma":0.000008164074,"domain_scores_codex":[0.9984946,0.0001799765,0.0005718775,0.000313416,0.0001723807,0.0002677435],"domain_scores_gemma":[0.9990175,0.0001632468,0.000426937,0.0002287527,0.0000629912,0.0001005686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001264027,0.0003344897,0.7733966,0.04920704,0.0001264362,6.308578e-7,0.00458685,0.00001372068,0.002174448,0.03137225,0.02339591,0.1152652],"study_design_scores_gemma":[0.02937179,0.007670853,0.1968087,0.2266159,0.00103757,0.0003806585,0.01924135,0.03914099,0.01801857,0.04395301,0.4117969,0.005963813],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8724133,0.09474268,0.001072402,0.00865704,0.01166032,0.004301642,0.00009417784,0.0001932379,0.006865232],"genre_scores_gemma":[0.9011832,0.005838964,0.06243327,0.02417309,0.00136256,0.001111023,0.001873073,0.0002153879,0.001809395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5765879,"threshold_uncertainty_score":0.7104273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03920398849542132,"score_gpt":0.3644642901111623,"score_spread":0.325260301615741,"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."}}