• 문화기술의 융합
• /
• 제8권6호
• /
• pp.1-7
• /
• 2022

이 연구는 119 응급 의료 서비스 팀을 위해 설계된 사전 및 사후 교육 실험을 활용하여 분류 교육 프로그램의 효과를 확인하기 위해 수행되었다. 목적: 이 연구는 분류 교육 프로그램에 참여한 119구급대원이 수행한 분류의 정확성에 대한 분류 교육 프로그램의 효과를 평가하였다. 연구 방법: 본 연구의 대상자는 119구급대원 119명으로, 프리젠테이션으로 구성된 20명의 모의환자가 제시되었다. 자료는 SPSS 21.0을 사용하여 분석하였다. 결과: 119명의 응급의료팀의 분류 정확도가 증가한 것으로 나타났다(p<.001). 그리고 과소 분류는 상당한 감소가 나타났다(p<.001). 또한 과대분류는 감소 되었으나 통계적으로 유의하지 않았다. 결론 : 본 연구에서 얻은 결과는 분류 교육 프로그램이 119구급대원의 다발성 부상 환자 또는 재난 피해자 분류의 정확성을 향상시키는데 효과적임을 보여주었다.

• 한국산학기술학회논문지
• /
• 제19권11호
• /
• pp.626-634
• /
• 2018

본 연구는 한국형응급환자분류도구(Korean Triage and Acuity Scale: KTAS)를 사용한 소아 중증도 분류의 정확성을 파악하기 위한 후향적 조사연구이다. 연구자료는 2016년 10월부터 2017년 9월까지 1개 권역응급의료센터, 1개 지역응급의료센터에 방문한 소아환자의 자료 중 무작위로 추출한 250건의 간호초진기록지와 진료결과였다. 수집된 자료를 검정된 전문가가 분석하여 true-triage를 정하였다. 중증도 분류 정확도는 응급실간호사의 중증도 분류 결과와 전문가의 true-triage결과와의 일치도로 평가하였다. 전문가 의견에 따라 중증도 분류 오류의 원인이 분석되었고, KTAS 등급과 퇴원, 체류시간, 진료비와의 연관성이 비교되었다. 연구결과 전문가와 응급실 간호사의 중증도 분류 등급은 높은 일치도를 보였다(weighted kappa=.77). 중증도 분류 불일치의 원인 중 활력징후 결과를 KTAS 알고리즘 기준에 잘 못 적용한 경우가 가장 많았다(n=13). KTAS 1,2 등급과 같이 중증도가 높을수록 퇴원이 적었다(${\chi}=43.25$, p<.001). 연령을 보정했을 때 KTAS 등급에 따라 체류시간(F=12.39, p<.001)과 진료비(F=11.78, p<.001)는 차이가 있었다. 본 연구결과 KTAS는 국내 응급실에서 높은 정확도를 보였으므로, 새로 개발된 중증도 분류 도구가 국내 응급실에 잘 적용되고 있다고 할 수 있다.

• 한국응급구조학회지
• /
• 제18권1호
• /
• pp.43-54
• /
• 2014

Purpose : The purpose of this study was to provide appropriate direction for triage education by investigating the knowledge level of triage in 119 EMTs before and after the triage education. Methods : The questionnaire was filled out by newly assigned 33 EMTs in the fire service academy in I metropolitan city from November 1, 2013. The data were analyzed using SPSS WIN 21.0 program. Results : The lowest knowledge level by 119 triage was the potential emergency related question, but that by case-based triage was the semi-emergency related questions. The knowledge score by case-based triage before education was 51.14 points. This was lower than knowledge score by 119 triage, that is, 75.70 points. After education, the knowledge level by 119 triage was significantly improved(p =.000). However, there was no significant difference in the knowledge level by case-based triage(p =.236). Conclusion : It is necessary to provide systematic and periodic education and training for 119 EMTs toward triage to improve triage accuracy and efficient circulation of the emergency medical service system. Especially, it is very important to provide case-based triage education for field application.

• 정보과학회 논문지
• /
• 제44권11호
• /
• pp.1156-1164
• /
• 2017

기존의 버그 담당자 자동 배정 연구들은 대부분 기계학습 알고리즘을 기반으로 예측 시스템을 구축하는 방식이었다. 따라서, 고성능의 기계학습 모델을 적용하는 것이 담당자 자동 배정 시스템 성능의 핵심이 된다고 할 수 있으며 관련 연구에서는 높은 성능을 보이는 SVM, Naive Bayes 등의 기계학습 모델들이 주로 사용되고 있다. 본 논문에서는 기계학습 분야에서 최근 좋은 성능을 보이고 있는 딥 러닝을 버그 담당자 자동 배정에 적용하고 그 성능을 평가한다. 실험 결과, 딥 러닝 기반 Bug Triage 시스템이 활성 개발자 대상 실험에서 48%의 정확도를 달성했으며 이는 기존의 기계학습 대비 최대 69%향상된 결과이다.

• 한국콘텐츠학회논문지
• /
• 제12권12호
• /
• pp.345-355
• /
• 2012

심뇌혈관 질환의 초기 처치가 지연되면 예후가 불량하고, 치료 후 심각한 후유증이 남으므로. 신속하고 적절한 처치를 위해 병원 전 단계 응급의료전화상담원에 의한 적절한 환자 분류와 병원 선정이 중요하다. 여러 선진국에서는 현장에 출동시킬 구급대 자원의 결정이나 각 병원에의 환자분산을 위해 응급의료전화상 담원이 표준화된 환자분류 지침을 사용하고 있다. 하지만, 우리나라의 경우 응급의료전화상담원의 심뇌혈관 환자 중증도 분류를 위한 표준화된 지침이 개발되어 있지 않다. 저자들은 영국의 NHS direct와 캐나다의 CTAS 체계에 기반하여, 뇌졸중 증상과 흉통 환자 분류를 위한 표준화 지침을 개발하였다. 환자가 내원한 응급실에서 시행된 중증도 분류를 기준으로 표준화된 지침을 사용한 군과 사용하지 않은 군을 비교하였다. 흉통환자에서 표준화된 지침을 사용한 군의 정확도가 높았다.(70.0% VS 94.0% p<0.01). 뇌졸중 환자에서도 같은 결과를 보였다. (64.2% VS 84.6% p<0.01). 결론적으로 응급의료정보센터의 응급의료전화상담원에 의한 뇌졸중 증상과 흉통 항목의 중증도 판단에 있어, 응급의료전화상담원의 주관적인 판단보다는 표준화된 지침을 이용한 판단이 병원에서 시행한 중증도 분류와 보다 일치하였다.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.967-985
• /
• 2019

Bug report processing is a key element of bug fixing in modern software maintenance. Bug reports are not processed immediately after submission and involve several processes such as bug report deduplication and bug report triage before bug fixing is initiated; however, this method of bug fixing is very inefficient because all these processes are performed manually. Software engineers have persistently highlighted the need to automate these processes, and as a result, many automation techniques have been proposed for bug report processing; however, the accuracy of the existing methods is not satisfactory. Therefore, this study focuses on surveying to improve the accuracy of existing techniques for bug report processing. Reviews of each method proposed in this study consist of a description, used techniques, experiments, and comparison results. The results of this study indicate that research in the field of bug deduplication still lacks and therefore requires numerous studies that integrate clustering and natural language processing. This study further indicates that although all studies in the field of triage are based on machine learning, results of studies on deep learning are still insufficient.

• 한국재난정보학회 논문집
• /
• 제14권1호
• /
• pp.28-35
• /
• 2018

본 연구에서는 재난현장 또는 일상에서 발생할 수 있는 다수사상자의 중증도 분류를 신속하고 정확하게 수행하기 위한 시스템을 설계하여 구현하였으며, 중증도 분류 알고리즘의 정확도뿐만 아니라 사용자 편의성 등 현장의 요구사항을 적극 반영하였다. 개발된 e-Triage System은 IoT개념을 활용하여 다양한 중증도 분류 알고리즘을 적용하였으며, 기존의 중증도 분류표의 단점을 극복하기 위하여 NFC 모듈 등 전자적 요소를 반영한 e-Triage Tag를 구현하였다. 앱으로 구현된 중증도 분류 알고리즘을 사용하여 신속하고 정확한 환자의 평가가 가능함을 입증하였고, 시인성을 위해 전자 중증도 분류 결과를 4가지 LED램프로 표출하였으며, 2차 분류를 통해 RTS 점수를 FND(Flexible Numeric Display)로 표출하였다.

• 기본간호학회지
• /
• 제19권4호
• /
• pp.444-452
• /
• 2012

Purpose: To explore the usefulness of previous fall history as a triage variable for inpatients. Methods: Medical records of 21,382 patients, admitted to medical units of one tertiary hospital, were analyzed retrospectively. Inpatient falls were identified from the hospital's self-report system. Non-falls in 1,125 patients were selected by a stratified matching sampling with 125 patients with falls (0.59%). A comparative and predictive accuracy analysis was conducted to describe differences between the two groups with and without a history of falls. Logistic regression was used to measure the effect size of the fall history. Results: The fall history group showed higher prevalence by 9 fold than the non-fall history group. The relationships between falls and relevant variables which were significant in the non-fall history group, were not significant for the fall history group. Falls in the fall history group were 25 times more likely than in the non-fall group. Predictive accuracy of the risk assessment tool showed almost zero specificity in the fall history group. Conclusion: The presence of fall history, the fall prevalence, variables relevant to falls, and the accuracy of the risk tool were different, which support the usefulness of the fall history as a triage variable.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권24호
• /
• pp.10961-10966
• /
• 2015

Background: Minor cervical cytologic abnormalities include atypical squamous cells of undetermined significance (ASC-US) and low-grade squamous intraepithelial lesion (LSIL). Approximately 10-20% of women with minor cytologic abnormalities have histologic high-grade squamous intraepithelial or worse lesions (HSIL+). In Thailand, women with minor cytologic abnormalities have a relatively high risk of cervical cancer, and referral for colposcopy has been suggested. A triage test is useful in the selection of women at risk for histologic HSIL+ to reduce the colposcopy burden. The aim of this study was to assess the performance of high-risk HPV DNA test in triage of women with minor cytologic abnormalities in northern Thailand. Materials and Methods: All women with ASC-US/LSIL cytology who were referred to our colposcopy clinic from October 2010 to February 2014 were included. HPV DNA testing was performed using Hybrid Capture 2 (HC2). All patients received colposcopic examination. Accuracy values of HC2 in predicting the presence of histologic HSIL+ were calculated. Results: There were 238 women in this study (121 ASC-US and 117 LSIL). The HC2 positivity rate was significantly higher in the LSIL group than in ASC-US group (74.8% versus 41.0%, p<0.001). Histologic HSIL+ was detected in 9 women (7.4%) in the ASC-US group and 16 women (13.7%) in the LSIL group (p=0.141). There was no histologic HSIL+ detected among HC2-negative cases (sensitivity and negative predictive value of 100%). The performance of HC2 triage was highest among women aged >50 years with ASC-US cytology. An increase in the cut-off threshold for positive HC2 resulted in a substantial decrease of sensitivity and negative predictive value. Conclusions: HPV DNA testing with HC2 shows very high sensitivity and negative predictive value in triage of women with minor cervical cytologic abnormalities in northern Thailand. An increase of the cut-off threshold for HC2 triage is not recommended in this region.

• Journal of Trauma and Injury
• /
• 제19권1호
• /
• pp.67-73
• /
• 2006

Purpose: The arterial base deficit (BD) has proven to be useful in the evaluation and management of trauma patients. Indicators such as the Triage-Revised Trauma Score (t-RTS) and the systemic inflammatory response syndrome (SIRS) score have been used as triage tools for emergency trauma patients in Korea. The purpose of this study was to assess the usefulness of the initial BD in predicting injury severity and outcome in the trauma population. Methods: The medical records of 308 consecutive trauma patients admitted to the Emergency Center of Masan Samsung Hospital from January 2004 to December 2004 were carefully examined prospectively and retrospectively, and 291 patients were selected as subjects for this research. The SIRS score and the t-RTS were calculated based on the records from the emergency department, and the BD was calculated based on the arterial blood gas analysis obtained within 30 minutes of admission. The efficiency of the three indicators as triage tools was evaluated by using cross tabulations in two - by - two matrices and by using a receiver operating characteristic (ROC) curve analysis. Results: When the mortality was used as the outcome parameter, the sensitivity and the accuracy of the initial BD were higher than those of the SIRS score (p<0.05) and were same as those of the t-RTS. The areas under the ROC curves of the initial BD, the SIRS score, and the t-RTS were $0.740{\pm}0.087$, $0.696{\pm}0.082$, and $0.871{\pm}0.072$, respectively (95% confidence interval). When emergency operation and blood transfusion requirements were used as outcome parameters, the comparisons of the sensitivities and the accuracies of the initial BD and the other two indicators showed the same pattern as mentioned above. The areas under the ROC curves of the initial BD were 0.7~0.8 and were larger than those of the SIRS score (p<0.05). Conclusion: The ability of the initial BD to predict injury severity and outcome was similar to those of the t-RTS and the SIRS score. Therefore, the authors suggest that the initial BD may be used as an alternative to previous triage tools for trauma patients.