• 제목/요약/키워드: Trauma model

검색결과 109건 처리시간 0.022초

A LightGBM and XGBoost Learning Method for Postoperative Critical Illness Key Indicators Analysis

  • Lei Han;Yiziting Zhu;Yuwen Chen;Guoqiong Huang;Bin Yi
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제17권8호
    • /
    • pp.2016-2029
    • /
    • 2023
  • Accurate prediction of critical illness is significant for ensuring the lives and health of patients. The selection of indicators affects the real-time capability and accuracy of the prediction for critical illness. However, the diversity and complexity of these indicators make it difficult to find potential connections between them and critical illnesses. For the first time, this study proposes an indicator analysis model to extract key indicators from the preoperative and intraoperative clinical indicators and laboratory results of critical illnesses. In this study, preoperative and intraoperative data of heart failure and respiratory failure are used to verify the model. The proposed model processes the datum and extracts key indicators through four parts. To test the effectiveness of the proposed model, the key indicators are used to predict the two critical illnesses. The classifiers used in the prediction are light gradient boosting machine (LightGBM) and eXtreme Gradient Boosting (XGBoost). The predictive performance using key indicators is better than that using all indicators. In the prediction of heart failure, LightGBM and XGBoost have sensitivities of 0.889 and 0.892, and specificities of 0.939 and 0.937, respectively. For respiratory failure, LightGBM and XGBoost have sensitivities of 0.709 and 0.689, and specificity of 0.936 and 0.940, respectively. The proposed model can effectively analyze the correlation between indicators and postoperative critical illness. The analytical results make it possible to find the key indicators for postoperative critical illnesses. This model is meaningful to assist doctors in extracting key indicators in time and improving the reliability and efficiency of prediction.

Factors Influencing Turnover Intention in Clinical Nurses: Compassion Fatigue, Coping, Social Support, and Job Satisfaction

  • Yang, Young Hee;Kim, Jong Kyung
    • 간호행정학회지
    • /
    • 제22권5호
    • /
    • pp.562-569
    • /
    • 2016
  • Purpose: This study was done to construct and verify a model of turnover intention in clinical nurses, considering the effects of compassion fatigue, coping, social support, and job satisfaction. Methods: For this study a cross-sectional correlational design was used. Participants were 283 clinical nurses in four general hospitals. Data were collected using a questionnaire and were analyzed with descriptive statistics, Pearson correlation coefficient and path analysis. Results: The modified model of turnover intention had a good fit in this study. Turnover intention was influenced by job satisfaction, and job satisfaction was affected by workload, problem-focused coping, peer support, family-friend support and compassion fatigue. Compassion fatigue was associated with occupational trauma events, problem-focused coping and emotional-focused coping. Job satisfaction was the most important factors controlling nurse's turnover intention. Conclusion: Findings show that job satisfaction, compassion fatigue, and traumatic events are important factors influencing turnover intention. Nurse managers try to manage job satisfaction, compassion fatigue, support, and coping for nurses, it could be expected making proper nursing circumstance.

단일 박동형 생명구조장치의 인공폐 적용 -실험연구- (Application of a Single-pulsatile Extracorporeal Life Support System for Extracorporeal Membrane Oxygenation -An experimental study -)

  • 김태식;선경;이규백;박성영;황재준;손호성;김광택;김형묵
    • Journal of Chest Surgery
    • /
    • 제37권3호
    • /
    • pp.201-209
    • /
    • 2004
  • 생명구조장치(ECLS)는 호흡부전 및 심부전에 적용하는 장치로 세계적으로 많은 연구개발과 임상시도가 계속되고 있다. 현재까지 생명구조장치의 혈류펌프로는 비박동형 구동장치가 표준으로 사용되고 있으며, 박동형 구동장치는 생리적인 측면에서 유리하지만 급격한 회로압 상승과 그에 따른 혈구손상에 대한 우려가 있고 특히 막형산화기를 사용하는 인공폐 회로에서 기피되어 왔다. 본 연구는 인공폐 실험모델에서 단일 박동형 구동펌프와 막형 산화기 사이에 압력완충장치를 설치함으로써 언급한 부작용을 최소화시키면서 생리적인 박동혈류를 유도할 수 있을 것이라는 가능성을 검증하였다. 실험대상은 올레익산으로 급성 호흡부전증이 유발된 잡견(N=16)을 사용하였다. 실험군은 사용된 구동펌프의 종류와 압력완충장치의 유무에 따라 3개 군으로 분류하였다. 제1군(n=6)은 대조군으로 원심펌프를 이용하였고, 제2군(n=4)은 단일 박동형 구동펌프를 사용하였으며, 제3군(n=6)은 단일 박동형 구동펌프에 압력완충장치를 설치하였다. 실험모델은 흉강 절개 후 우심방-대동맥을 우회시키는 부분 체외순환 형태로, 1.8~2 L/min의 펌프박출량에서 2시간을 구동하였다. 관찰지표는 주로 혈역학 변화, 회로압, 혈액검사 및 혈구세포에 미치는 영향 등에 한정하였다. 맥동압(pulse pressure)은 박동형 구동펌프를 이용한 2군(47$\pm$10 mmHg)과 3군(41$\pm$9 mmHg)에서 비박동형 원심펌프를 이용한 1군(17$\pm$7 mmHg)에 비해 유의하게 높았다(p<0.001). 막형산화기에 걸리는 회로압은 1 군의 경우 222$\pm$8mmHg, 2군의 경우 739 $\pm$ 35 mmHg, 3군의 경우 470$\pm$ 17 mmHg였다(p<0.001). 순환 2시간째의 동맥혈 산소분압은 1군에 비해 박동혈류를 사용하는 2군과 3군에서 현저하게 높았다(77$\pm$41, 96$\pm$48, 97$\pm$25 mmHg; p<0.05). 혈구손상지표인 혈장 유리 헤모글로빈치는 1군에서 가장 낮았고, 2군에서 가장 높았으며, 3군에서 유의하게 감소하였다(55.7$\pm$43.3, 162.8$\pm$113.6, 82.5$\pm$25.1 mg%; p<0.05). 기타 혈액검사치는 특별한 차이가 없었다. 이상의 결과에서 단일 박동형 구동펌프는 비박동형 원심펌프에 비해 막형산화기의 산소교환에 유리한 반면, 회로압과 혈구세포 손상 측면에서 불리하다는 것을 알 수 있었다. 그러나 단일 박동형 구동펌프와 막형 산화기 사이에 압력완충장치를 설치하는 경우, 회로압 상승과 혈구세포손상을 유의하게 감소시킬 수 있었다.

실험적 외상성 뇌손상모델에서 외상 후 저체온과 MgSO4의 효과 (Effects of Posttraumatic MgSO4 Injection and Hypothermia an Animal Model of Traumatic Brain Injury(TBI))

  • 한성록;현동근;박종운;하영수;김준미
    • Journal of Korean Neurosurgical Society
    • /
    • 제29권10호
    • /
    • pp.1296-1302
    • /
    • 2000
  • Objective : Traumatic brain injury including diffuse axonal injury has been shown to result in a decrease in brainfree magnesium concentration, an endogenous inhibitor of calcium entry into neuron, that is associated with the development of neurological motor deficits. The goal of this study is to establish the therapeutic window during which the therapy with $MgSO_4$ and/or hypothermia improve damaged neurons by TUNEL stain. Method : Moderate brain injury was induced in 64 adult Sprague-Dawley rats, weighing 350 to 450gm each, by using a simple weight-drop device(Marmarou model). The animals were randomly assigned to four groups(sixteen rats each, a control group, a group treated with $MgSO_4$, a group treated with hypothermia, and a group treated with $MgSO_4$ and hypothermia) and the rats in each group were sacrificed and studied after 12 hrs, 24 hrs, 1 wk, and 2 wks after insult. In hypothermic group, these rats were subjected to hypothermia after injury, with their rectal temperatures maintained at $32^{\circ}C$ for 1 hour. After 1-hour period of hypothermia, rewarming to normothermic level was accomplished over 30-minute period. In the groups treated $MgSO_4$, hypothermia and $MgSO_4$ were subsequently treated with $MgSO_4$($750{\mu}moles/kg$) infused intra-muscularly at 30 minutes after trauma. Result : In all treated groups, a significant reduction in TUNEL positive cells was found in comparison with the control group each time(p<0.001). Between treatment groups, No differnce was seen 12hrs, 24hrs, and 1wk. However, hypothermic group treated with or without $MgSO_4$ showed more significant reduction in apoptotic cells than group treated with $MgSO_4$ 2 weeks after trauma(p<0.05). However, hypothermic group treated with $MgSO_4$ showed no significant reduction in apoptotic cells compared with hypothermic group(p>0.05). Conclusion : These findings suggest that both hypothermia and $MgSO_4$ significantly improve pathological changes. Otherwise simultaneously $MgSO_4$ and hypothermia treatment groups is failed to provide additional neuroprotection. These results may be relevant to the design of future clinical trials of therapeutic hypothermia and $MgSO_4$ for traumatic brain injury.

  • PDF

사후전산화단층촬영의 법의병리학 분야 활용을 위한 조건부 적대적 생성 신경망을 이용한 CT 영상의 해상도 개선: 팬텀 연구 (Enhancing CT Image Quality Using Conditional Generative Adversarial Networks for Applying Post-mortem Computed Tomography in Forensic Pathology: A Phantom Study)

  • 윤예빈;허진행;김예지;조혜진;윤용수
    • 대한방사선기술학회지:방사선기술과학
    • /
    • 제46권4호
    • /
    • pp.315-323
    • /
    • 2023
  • Post-mortem computed tomography (PMCT) is commonly employed in the field of forensic pathology. PMCT was mainly performed using a whole-body scan with a wide field of view (FOV), which lead to a decrease in spatial resolution due to the increased pixel size. This study aims to evaluate the potential for developing a super-resolution model based on conditional generative adversarial networks (CGAN) to enhance the image quality of CT. 1761 low-resolution images were obtained using a whole-body scan with a wide FOV of the head phantom, and 341 high-resolution images were obtained using the appropriate FOV for the head phantom. Of the 150 paired images in the total dataset, which were divided into training set (96 paired images) and validation set (54 paired images). Data augmentation was perform to improve the effectiveness of training by implementing rotations and flips. To evaluate the performance of the proposed model, we used the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and Deep Image Structure and Texture Similarity (DISTS). Obtained the PSNR, SSIM, and DISTS values of the entire image and the Medial orbital wall, the zygomatic arch, and the temporal bone, where fractures often occur during head trauma. The proposed method demonstrated improvements in values of PSNR by 13.14%, SSIM by 13.10% and DISTS by 45.45% when compared to low-resolution images. The image quality of the three areas where fractures commonly occur during head trauma has also improved compared to low-resolution images.

기계학습을 적용한 자기보고 증상 기반의 어혈 변증 모델 구축 (Machine Learning Approach to Blood Stasis Pattern Identification Based on Self-reported Symptoms)

  • 김현호;양승범;강연석;박영배;김재효
    • Korean Journal of Acupuncture
    • /
    • 제33권3호
    • /
    • pp.102-113
    • /
    • 2016
  • Objectives : This study is aimed at developing and discussing the prediction model of blood stasis pattern of traditional Korean medicine(TKM) using machine learning algorithms: multiple logistic regression and decision tree model. Methods : First, we reviewed the blood stasis(BS) questionnaires of Korean, Chinese, and Japanese version to make a integrated BS questionnaire of patient-reported outcomes. Through a human subject research, patients-reported BS symptoms data were acquired. Next, experts decisions of 5 Korean medicine doctor were also acquired, and supervised learning models were developed using multiple logistic regression and decision tree. Results : Integrated BS questionnaire with 24 items was developed. Multiple logistic regression models with accuracy of 0.92(male) and 0.95(female) validated by 10-folds cross-validation were constructed. By decision tree modeling methods, male model with 8 decision node and female model with 6 decision node were made. In the both models, symptoms of 'recent physical trauma', 'chest pain', 'numbness', and 'menstrual disorder(female only)' were considered as important factors. Conclusions : Because machine learning, especially supervised learning, can reveal and suggest important or essential factors among the very various symptoms making up a pattern identification, it can be a very useful tool in researching diagnostics of TKM. With a proper patient-reported outcomes or well-structured database, it can also be applied to a pre-screening solutions of healthcare system in Mibyoung stage.

Intracranial Pressure and Experimental Model of Diffuse Brain Injury in Rats

  • Blaha, Martin;Schwab, Juraj;Vajnerova, Olga;Bednar, Michal;Vajner, Ludek;Michal, Tichy
    • Journal of Korean Neurosurgical Society
    • /
    • 제47권1호
    • /
    • pp.7-10
    • /
    • 2010
  • Objective: In this study, we present a simple closed head injury model as a two-stage experiment. The height of the weight drop enables gradation of head trauma severity. Methods: The head injury device consists of three parts and there are three adjustable parameters-weight (100-600 g). height of fall (5-100 cm) and elasticity of the springs. Thirty male Wistar rats underwent monitoring of intracranial pressure with and without induction of the head injury. Results: The weight drop from 45 to 100 cm led to immediate seizure activity and early death of the experimental animals. Severe head injury was induced from 40 cm weight drop. There was 50% mortality and all surviving rats had behavioral deterioration. Intracranial pressure was 9.3${\pm}$3.76 mmHg. Moderate head injury was induced from 35 cm, mortality decreased to 20-40%, only half of the animals showed behavioral pathology and intracranial pressure was 7.6${\pm}$3.54 mmHg. Weight drop from 30 cm caused mild head injury without mortality and neurological deterioration. Intracranial pressure was slightly higher compared to sham group- 5.5${\pm}$0.74 mmHg and 2.9${\pm}$0.81 mmHg respectively. Conclusion: This model is an eligible tool to create graded brain injury with stepwise intracranial pressure elevation.

백서의 패혈증 모델에서 시간에 따른 폐조직에서의 Inducible Nitric Oxide Synthase 발현 (Time Course of Inducible NOS Expression of Lung Tissue during Sepsis in a Rat Model)

  • 김중희;김성춘;권운용;서길준;윤여규
    • Journal of Trauma and Injury
    • /
    • 제21권2호
    • /
    • pp.120-127
    • /
    • 2008
  • Purpose: Many studies on the time course of inducible nitric oxide synthase (iNOS) gene expression have been performed in the LPS (Lipopolysaccharide)-induced endotoxemic model, but there have been few experimental approaches to continuous peritonitis-induced sepsis model. We conducted this study to establish basic data for future sepsis-related research by investigating the time course of iNOS gene expression and the relationship with the production of inflammatory mediators in the early sepsis model induced by cecal ligation and puncture (CLP). Methods: Male Sprague-Dawley rats were operated on by sing the CLP method to induce of peritonitis; and then, they were sacrificed and samples of blood and lung tissues were obtained at various times (1,2,3,6,9 and 12 h after CLP). We observed the expression of iNOS mRNA from lung tissues and measured the synthesis of nitric oxide, $IL-1{\beta}$, and $TNF-{\alpha}$ from the blood. Results: iNOS mRNA began to be expressed at 3 h and was maintained untill 12 h after CLP. The nitric oxide concentration was increased significantly at 6 h, reached its peak level at 9 h, and maintained a plateau untill 12 h after CLP. $TNF-{\alpha}$ began to be detected at 3 h, increased gradually, and decreased steeply from 9 h after CLP. $IL-1{\beta}$ showed its peak level at 6 h after CLP, and tended to decrease without significance. Conclusion: We observed that the iNOS gene was expressed later in peritonitis-induced sepsis than in LPS-induced sepsis. Nitric oxide and key inflammatory mediators were also expressed later in peritonitis-induced sepsis than in LPS-induced sepsis.

Accuracy of Bite Registration Using Intraoral Scanner Based on Data Trimming Strategy for Fremitus Teeth

  • Jeong, Yuwon;Shim, June-Sung;Kim, Jee-Hwan;Kim, Jong-Eun;Lee, Hyeonjong
    • Journal of Korean Dental Science
    • /
    • 제15권1호
    • /
    • pp.61-67
    • /
    • 2022
  • Purpose: This study aimed to evaluate the accuracy of bite registration using intraoral scanner based on data trimming strategy for fremitus teeth. Materials and Methods: A reference model was designed by Medit Model Builder software (MEDIT Corp., Seoul). Tooth number 24 and 25 were separated as dies and tooth number 26 was prepared for full-coverage crown. Those were printed using a 3D printer (NextDent 5100). The scanning procedure was performed by a single trained operator with one intraoral scanner (i700; MEDIT Corp.). The scanning groups were divided as follows: group 1 (G1), no fremitus; group 2 (G2), 0.5 mm buccal fremitus in the maxillary left first and second premolar; and group 3 (G3), 1.5 mm buccal fremitus in the maxillary left first and second premolar. Each group was scanned 10 times and were analyzed using the reference model data. Surface-based occlusal clearance was analyzed at the prepared tooth to evaluate accuracy. Result: Mean values of control group (G1) were 1.587±0.021 mm. G2 showed similar values to those from the control group (1.580±0.024 mm before trimming strategy and 1.588±0.052 mm after trimming strategy). G3 showed significantly greater values (1.627±0.025 mm before trimming strategy and 1.590±0.024 mm after trimming strategy) and the differences were found between trimming strategy (P=0.004). Conclusion: Bite trimming strategy for fremitus teeth is a reliable technique to reduce inaccuracies caused by the mobility at maximum intercuspation.

심한 정신적 외상 경험을 한 학령 전기 아동의 정신적 표상에 대한 예비연구 (PRELIMINARY STUDY OF MENTAL REPRESENTATIONS OF PRESCHOOL CHILDREN EXPERIENCING SINGLE, SEVERE TRAUMA)

  • 엄소용;송원영;오경자;최의겸;심은지;신의진
    • Journal of the Korean Academy of Child and Adolescent Psychiatry
    • /
    • 제15권1호
    • /
    • pp.61-74
    • /
    • 2004
  • 연구목적:아동기에 경험한 심각한 정신적 외상은 외상후 스트레스 장애(Posttraumatic Stress Disorder;PTSD) 증상을 야기할 뿐 아니라, 전반적인 심리 발달에도 부정적인 영향을 미친다. 특히 정신적 외상은 학령전기 아동의 정신적 표상에 부정적인 영향을 미쳐 향후 인격형성에 문제를 일으킬 것으로 예상된다. 본 연구는 한차례의 심한 정신적 외상을 경험한 9명의 학령전기 아동들의 심리적 표상이 어떻게 형성되어 있는지를 조사하여 이들의 정신적 문제를 진단적 범주 차원을 넘어 내면의 심리적 차원의 이해를 높이고자 하였다. 방 법:유치원 점심시간에 침입한 정신질환자에게 칼로 심한 신체적 상해를 입은 동일한 한 차례의 심한 정신적 외상을 경험한 만 $3{\sim}5$세 아동 9명(남아 6명, 여아 3명)을 대상으로, 사고 발생 1개월 경과 후 신체적 상해를 치료한 시점에서 심리적 평가를 시행하였다. 평가는 부모 면담, 아동에 대한 정신의학적 면담 및 관찰, 아동에 대한 심리평가(지능검사, House-Tree-Person test;HTP, MacArthur Stem Story Battery;MSSB) 등이 포괄적으로 이루어졌다. 본 연구에서는 아동의 정신적 표상을 반영하는 MSSB, HTP 검사 결과를 분석하였다. 결 과:9명의 아동은 모두 진단(5명이 PTSD 진단에 해당됨)과 상관없이 보편적으로 외상 경험과 관련되어 보이는 높은 불안감, 우울감, 위축과 회피 등의 감정 반응을 주로 나타내었는데, 이런 반응들은 부모 보고에 의한 평가에서는 거의 나타나지 않았다. 특히 병원 치료에 대한 공포, 사고에 대한 재현, 공격적 주제, 양육자와의 이별 등의 내용이 아동의 그림이나 이야기 속에서 자주 나타났으며 이런 내용은 직접적 질문이나 대화에서는 거의 나타나지 않았다. 결 론:본 연구에서 한번의 심각한 외상 경험을 한 학령 전기 아동들은 PTSD 진단 여부와 관계없이, 전반적 정신적 표상으로 외상과 관련된 부정적 정서 경험과 사고 내용을 보였다. 따라서 향 후 심한 정신적 충격을 받은 학령전기 아동들의 경우 PTSD 증상 뿐 아니라 사고로 야기된 부정적 정신적 표상에 대한 평가와 개입이 필요하다고 판단된다.

  • PDF