{"id":"W2053479646","doi":"10.4137/bii.s4706","title":"Suicide Note Classification Using Natural Language Processing: A Content Analysis","year":2010,"lang":"en","type":"article","venue":"Biomedical Informatics Insights","topic":"Mental Health via Writing","field":"Psychology","cited_by":239,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; Windsor Clinical Research","funders":"U.S. National Library of Medicine","keywords":"Categorization; Mental health; Suicide prevention; Psychology; Occupational safety and health; Human factors and ergonomics; Injury prevention; Poison control; Suicide attempt; Artificial intelligence; Psychiatry; Machine learning; Medicine; Medical emergency; Computer science","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":[0.0004349494,0.0001827206,0.0003117186,0.000522443,0.0002317888,0.00007571426,0.0002888988,0.0002795829,0.0003676259],"category_scores_gemma":[0.0001349658,0.0001433049,0.0001095506,0.001025441,0.0002653697,0.0002729045,0.00006796415,0.0006673848,0.0002026863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049065,"about_ca_system_score_gemma":0.000108451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000274283,"about_ca_topic_score_gemma":0.0001649068,"domain_scores_codex":[0.9977963,0.0000554432,0.001006522,0.0001738767,0.0005360953,0.0004317946],"domain_scores_gemma":[0.9985893,0.0001220961,0.00045148,0.0003997938,0.0001192481,0.0003180847],"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":[0.0002674094,0.001389229,0.008087795,0.001154797,0.001013091,0.0001520097,0.1863772,0.000005469695,0.1217456,0.02296129,0.001518336,0.6553277],"study_design_scores_gemma":[0.002843698,0.000197441,0.06491797,0.0002576497,0.0007404691,0.0001770044,0.03880273,0.8700947,0.001890624,0.0001810492,0.01891656,0.0009800746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9800427,0.0003784898,0.01116763,0.0001807856,0.001263651,0.0003161494,0.00001302202,0.000136759,0.006500846],"genre_scores_gemma":[0.9861374,0.000001995684,0.01214248,0.0009848019,0.0002651619,0.00002285358,0.0001924129,0.00001487588,0.0002380246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8700892,"threshold_uncertainty_score":0.5843806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1168740545948059,"score_gpt":0.42183088917571,"score_spread":0.3049568345809041,"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."}}