{"id":"W4393987900","doi":"10.1093/aje/kwae030","title":"Using unsupervised clustering approaches to identify common mental health profiles and associated mental health-care service-use patterns in Ontario, Canada","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario","funders":"University of Toronto; Ontario Ministry of Health and Long-Term Care","keywords":"Mental health; Population; Health care; Distress; Cluster analysis; Mental distress; Medical diagnosis; Psychology; Medicine; Psychiatry; Gerontology; Clinical psychology; Environmental health; Computer science; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.00138754,0.0004427297,0.0005023171,0.003685017,0.00305659,0.001630248,0.00114254,0.0003361166,0.001059015],"category_scores_gemma":[0.005248211,0.0002580569,0.0008156804,0.006643944,0.0005972835,0.0003246494,0.00123564,0.0003528516,0.0001473358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02865823,"about_ca_system_score_gemma":0.04018128,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9920366,"about_ca_topic_score_gemma":0.9951329,"domain_scores_codex":[0.9986954,0.0002492036,0.0001101147,0.0002965477,0.0003244177,0.0003242513],"domain_scores_gemma":[0.9975123,0.0003497682,0.0003465546,0.0001445494,0.001484518,0.0001622835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002749177,0.0001192983,0.8860748,0.0003096987,0.0004065299,0.0002564769,0.008900493,0.008299075,0.002100556,0.002252247,0.01107116,0.07993476],"study_design_scores_gemma":[0.00003443925,0.00003365485,0.9458022,0.0001053938,0.0001038251,0.00007277668,0.008354852,0.03575119,0.0006111348,0.001264834,0.007794674,0.00007096076],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586907,0.000828755,0.0204875,0.0008493843,0.00003412203,0.0006187372,0.01323519,0.0001861935,0.005069345],"genre_scores_gemma":[0.9625923,0.000400073,0.02312705,0.0001239269,0.00001006347,0.0002698653,0.01085647,0.00003838894,0.002581726],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02865823,"threshold_uncertainty_score":0.207931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1889295069494409,"score_gpt":0.4081297211625891,"score_spread":0.2192002142131482,"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."}}