{"id":"W3020889794","doi":"10.2196/14500","title":"Identifying the Medical Lethality of Suicide Attempts Using Network Analysis and Deep Learning: Nationwide Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Suicide and Self-Harm Studies","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Korea Institute of Science and Technology Information; National Supercomputing Center, Korea Institute of Science and Technology Information; National Institutes of Health; Korea Institute of Science and Technology","keywords":"Antecedent (behavioral psychology); Suicide methods; Suicide prevention; Poison control; Injury prevention; Human factors and ergonomics; Suicide attempt; Lethality; Psychology; Medicine; Clinical psychology; Psychiatry; Medical emergency; Developmental psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001232184,0.0005499227,0.0003566072,0.001600589,0.0003442688,0.0004989659,0.0005575834,0.0005816749,0.000800907],"category_scores_gemma":[0.005274673,0.0002652766,0.0008443221,0.0008085342,0.0002722852,0.0007387224,0.0008546497,0.0009734872,0.0002770561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006954916,"about_ca_system_score_gemma":0.000641502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01118969,"about_ca_topic_score_gemma":0.01489413,"domain_scores_codex":[0.9993777,0.0002322969,0.00006797702,0.0001539691,0.00009198087,0.00007603226],"domain_scores_gemma":[0.9978763,0.0006435775,0.0005190347,0.0002718335,0.0004608195,0.0002284788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001590979,0.0004247239,0.9709215,0.00006083314,0.0002026913,0.0001777277,0.0001592287,0.002427512,0.0002844504,0.0001408469,0.001104267,0.02393718],"study_design_scores_gemma":[0.00005121305,0.0005138834,0.8546086,0.0001148972,0.0004376745,0.0006910964,0.001263723,0.138737,0.001078084,0.00114754,0.001299454,0.00005686007],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971513,0.0001504174,0.001593437,0.0001279468,0.000009708891,0.00002788479,0.000664511,0.00001819959,0.0002566403],"genre_scores_gemma":[0.996673,0.0001764273,0.00138726,0.0000483796,0.00001202393,0.00003926375,0.001461386,0.000004434396,0.0001978666],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01118969,"threshold_uncertainty_score":0.02224916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07758419796131528,"score_gpt":0.3966309868580468,"score_spread":0.3190467888967315,"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."}}