{"id":"W3213968965","doi":"10.1371/journal.pone.0258400","title":"Treatment selection using prototyping in latent-space with application to depression treatment","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Mental Health Research Topics","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Ministry of Health, State of Israel","keywords":"Major depressive disorder; Computer science; Cluster analysis; Machine learning; Depression (economics); Personalized medicine; Selection (genetic algorithm); Artificial intelligence; Psychology; Data science; Medicine; Bioinformatics; Psychiatry; Biology; Cognition","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":[0.00006044219,0.0001084868,0.0001662621,0.00009800504,0.00008342695,0.0000152562,0.00003717428,0.00006036239,0.0001402506],"category_scores_gemma":[0.0000083899,0.00008891649,0.00001497824,0.0003508605,0.000008779418,0.00004319387,0.00001708044,0.00007379292,0.00009512989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001150901,"about_ca_system_score_gemma":0.00009869938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001272703,"about_ca_topic_score_gemma":0.001084027,"domain_scores_codex":[0.9988642,0.0001394941,0.0001477945,0.0003548721,0.0001931056,0.0003005888],"domain_scores_gemma":[0.9995103,0.00002948141,0.00004199506,0.0002368942,0.00005807716,0.0001232744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001547561,0.0153405,0.6487332,0.000239901,0.0003351851,0.0001190891,0.004508077,0.0002989222,0.1907904,0.0004478436,0.00001117218,0.1376282],"study_design_scores_gemma":[0.007869276,0.005807285,0.2006879,0.0009631405,0.0001768885,0.00007473423,0.0007514583,0.01532018,0.7649925,0.0001056061,0.002721731,0.0005292444],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941157,0.0001786191,0.0009719538,0.0006654593,0.00001621973,0.002848616,0.000003315399,0.00004069397,0.00115944],"genre_scores_gemma":[0.9836738,0.00004931275,0.01064513,0.00005668801,0.00008387434,0.002793521,0.00002440043,0.00002604084,0.002647216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5742022,"threshold_uncertainty_score":0.3625909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1635039563995122,"score_gpt":0.4100538020469447,"score_spread":0.2465498456474325,"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."}}