{"id":"W4407246962","doi":"10.1371/journal.pdig.0000734","title":"Forecasting mental states in schizophrenia using digital phenotyping data","year":2025,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Mental Health Research Topics","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Douglas Mental Health University Institute","funders":"Fonds de Recherche du Québec - Santé; Courtois Foundation","keywords":"Artificial intelligence; Machine learning; Computer science; Ordinal data; Binary classification; Ordinal regression; Regression; Skewness; Gradient boosting; Binary number; Schizophrenia (object-oriented programming); Statistics; Support vector machine; Random forest; Mathematics","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":[0.0004521337,0.0002342516,0.0003836516,0.0003639104,0.0002538484,0.0003357255,0.0006700099,0.00008519964,0.000105451],"category_scores_gemma":[0.0002097674,0.0002441523,0.00003642392,0.0006417895,0.0001107226,0.001222396,0.0007977726,0.0004828832,0.0001040679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007191992,"about_ca_system_score_gemma":0.000590469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006014486,"about_ca_topic_score_gemma":0.0001998654,"domain_scores_codex":[0.9968698,0.0001041042,0.0007812734,0.0007273926,0.0003785397,0.001138876],"domain_scores_gemma":[0.9983722,0.0003018252,0.0001611538,0.0008209045,0.00003921944,0.0003046729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000869327,0.001591356,0.06181742,0.001366457,0.0001259498,0.00008533514,0.00251964,0.00002140042,0.00001048269,0.003576125,0.004180468,0.9238361],"study_design_scores_gemma":[0.02564607,0.002340139,0.04525087,0.01199823,0.00005375874,0.0003089548,0.02824103,0.7830237,0.0001537151,0.03660502,0.06305163,0.003326942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9657068,0.001763398,0.0005155861,0.00161841,0.0007098889,0.001360176,0.001616393,0.0001372308,0.02657213],"genre_scores_gemma":[0.9965077,0.00002791508,0.0006263413,0.0007113927,0.0001250443,0.00002333679,0.001049516,0.00004031008,0.000888433],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9205091,"threshold_uncertainty_score":0.9956241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2561580101767793,"score_gpt":0.456723695974789,"score_spread":0.2005656857980097,"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."}}