OBJECTIVE: The purpose of this study was to identify the factors that influence the consent of case management for suicide prevention. METHODS: This study included 232 suicide attempters from September 1, 2015 to August 31, 2016 at the Emergency Medical Center of Soonchunhyang University Bucheon Hospital, Korea. A retrospective chart analysis was performed using a chi-square test or Fisher exact test, as well as univariate and multivariate logistic regression analysis (R ver. 3.3.3). RESULTS: The positive factors affecting case management consent were direct face-to-face counseling with a case manager, patient's age, suicide attempt without alcohol, first suicide attempt, and no psychiatric history. In addition, suicide attempters who underwent follow-up case management were more likely to participate in outpatient mental health care. Through the case manager, continuous emotional support and encouragement were provided to the suicide attempt, which proved to be effective. CONCLUSION: This study emphasizes the importance of case management for suicide attempters visiting the emergency medical center and suggests that the cooperation of national and regional systems should be expanded to increase the case participation rate.
Case Management* ; Counseling ; Emergencies* ; Emergency Service, Hospital* ; Follow-Up Studies* ; Gyeonggi-do ; Humans ; Korea ; Logistic Models ; Mental Health ; Outpatients ; Retrospective Studies ; Suicide* ; Suicide, Attempted

Background: Rapid triage reduces the patients' stay time at an emergency department (ED). The Korean Triage Acuity Scale (KTAS) is mandatorily applied at EDs in South Korea.For rapid triage, we studied machine learning-based triage systems composed of a speech recognition model and natural language processing-based classification. Methods: We simulated 762 triage cases that consisted of 18 classes with six types of the main symptom (chest pain, dyspnea, fever, stroke, abdominal pain, and headache) and three levels of KTAS. In addition, we recorded conversations between emergency patients and clinicians during the simulation. We used speech recognition models to transcribe the conversation. Bidirectional Encoder Representation from Transformers (BERT), support vector machine (SVM), random forest (RF), and k-nearest neighbors (KNN) were used for KTAS and symptom classification. Additionally, we evaluated the Shapley Additive exPlanations (SHAP) values of features to interpret the classifiers. Results: The character error rate of the speech recognition model was reduced to 25.21% through transfer learning. With auto-transcribed scripts, support vector machine (area under the receiver operating characteristic curve [AUROC], 0.86; 95% confidence interval [CI], 0.81–0.9), KNN (AUROC, 0.89; 95% CI, 0.85–0.93), RF (AUROC, 0.86; 95% CI, 0.82–0.9) and BERT (AUROC, 0.82; 95% CI, 0.75–0.87) achieved excellent classification performance.Based on SHAP, we found “stress”, “pain score point”, “fever”, “breath”, “head” and “chest” were the important vocabularies for determining KTAS and symptoms. Conclusion We demonstrated the potential of an automatic KTAS classification system using speech recognition models, machine learning and BERT-based classifiers.

Background: Rapid triage reduces the patients' stay time at an emergency department (ED). The Korean Triage Acuity Scale (KTAS) is mandatorily applied at EDs in South Korea.For rapid triage, we studied machine learning-based triage systems composed of a speech recognition model and natural language processing-based classification. Methods: We simulated 762 triage cases that consisted of 18 classes with six types of the main symptom (chest pain, dyspnea, fever, stroke, abdominal pain, and headache) and three levels of KTAS. In addition, we recorded conversations between emergency patients and clinicians during the simulation. We used speech recognition models to transcribe the conversation. Bidirectional Encoder Representation from Transformers (BERT), support vector machine (SVM), random forest (RF), and k-nearest neighbors (KNN) were used for KTAS and symptom classification. Additionally, we evaluated the Shapley Additive exPlanations (SHAP) values of features to interpret the classifiers. Results: The character error rate of the speech recognition model was reduced to 25.21% through transfer learning. With auto-transcribed scripts, support vector machine (area under the receiver operating characteristic curve [AUROC], 0.86; 95% confidence interval [CI], 0.81–0.9), KNN (AUROC, 0.89; 95% CI, 0.85–0.93), RF (AUROC, 0.86; 95% CI, 0.82–0.9) and BERT (AUROC, 0.82; 95% CI, 0.75–0.87) achieved excellent classification performance.Based on SHAP, we found “stress”, “pain score point”, “fever”, “breath”, “head” and “chest” were the important vocabularies for determining KTAS and symptoms. Conclusion We demonstrated the potential of an automatic KTAS classification system using speech recognition models, machine learning and BERT-based classifiers.

OBJECTIVE: The purpose of this study was to analyze the characteristics and factors of voluntary discharged patients after suicide attempt and analyze the effectiveness of follow-up measures. METHODS: Total 504 adult patients aged 14 years and over, who visited a local emergency medical center from September 1, 2013 to December 31, 2015 were enrolled and retrospectively reviewed. We analyzed the relationship with voluntary discharge group (VDG) among basic characteristics, suicidal attempt variables, outcome variables related to suicide attempts, and treatment related variables comparing with normal discharge group (NDG). RESULTS: Of the total 504 suicide attempts, three hundred eleven (61.7%) patients were VDG and 193 (38.2%) were NDG. The proportion of patients who completed the community service linkage were 18.7% (36/193) in NDG, compared with 7.7% (24/311) in VDG (p < 0.05). In addition, the ratio of the patients who visited psychiatric outpatient department in NDG were 57.0% (110/193), more than four times as likely as 14.5% (45/311) in VDG (p < 0.05). CONCLUSION: Over sixty percent of suicide attempters discharged against medical advice. Further various aspects of national supportive measures including strengthening case management service should be considered.
Adult ; Case Management ; Emergencies* ; Emergency Service, Hospital* ; Follow-Up Studies ; Humans ; Linear Energy Transfer* ; Outpatients ; Retrospective Studies ; Social Welfare ; Suicide ; Suicide, Attempted*