{"id":"W4405626767","doi":"10.1101/2024.12.17.24319152","title":"Clinical and Biological Stratification in 121,560 Antidepressant Prescription Trajectories using Unsupervised Modelling and Clustering","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Mental Health Research Topics","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Biological Sciences","funders":"NIHR Maudsley Biomedical Research Centre; Novo Nordisk Fonden; King's College London; Department of Health and Social Care; Novo Nordisk; National Institute for Health and Care Research","keywords":"Stratification (seeds); Cluster analysis; Antidepressant; Medical prescription; Computer science; Artificial intelligence; Psychology; Medicine; Biology; Neuroscience; Pharmacology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002451531,0.0003182904,0.0006091543,0.001707767,0.0004596697,0.00102892,0.0007489527,0.0005874696,0.001290749],"category_scores_gemma":[0.009134679,0.000261419,0.001024138,0.002444492,0.0002742907,0.0002834228,0.0008196997,0.0004820351,0.0007696207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007060135,"about_ca_system_score_gemma":0.0008776285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02115646,"about_ca_topic_score_gemma":0.01505173,"domain_scores_codex":[0.9984239,0.0005673641,0.0002167467,0.0004925157,0.0001755095,0.0001239169],"domain_scores_gemma":[0.9965659,0.001503981,0.0006348851,0.0007211728,0.0004422877,0.0001318891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000728178,0.0001474041,0.9368114,0.0001624891,0.0004849466,0.0003102122,0.0006970746,0.01656856,0.002777339,0.001037744,0.005777474,0.03449715],"study_design_scores_gemma":[0.0001219384,0.0001648266,0.8098252,0.0001436721,0.0003335519,0.0005036926,0.0005248149,0.1747783,0.001886792,0.004421724,0.007196897,0.00009871217],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9569186,0.0004189433,0.02032844,0.0002434182,0.00002549524,0.0001123125,0.02125764,0.0001578301,0.0005373406],"genre_scores_gemma":[0.9457432,0.0001868219,0.01297204,0.00006343916,0.00001401203,0.0002051678,0.04003388,0.00003179929,0.0007495615],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02115646,"threshold_uncertainty_score":0.04206663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3402927605945587,"score_gpt":0.4725421371360267,"score_spread":0.1322493765414681,"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."}}