• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.126-136
• /
• 2018

The purpose of this study was to develop a severity-adjustment model for predicting mortality in acute stroke patients using machine learning. Using the Korean National Hospital Discharge In-depth Injury Survey from 2006 to 2015, the study population with disease code I60-I63 (KCD 7) were extracted for further analysis. Three tools were used for the severity-adjustment of comorbidity: the Charlson Comorbidity Index (CCI), the Elixhauser comorbidity index (ECI), and the Clinical Classification Software (CCS). The severity-adjustment models for mortality prediction in patients with acute stroke were developed using logistic regression, decision tree, neural network, and support vector machine methods. The most common comorbid disease in stroke patients were hypertension, uncomplicated (43.8%) in the ECI, and essential hypertension (43.9%) in the CCS. Among the CCI, ECI, and CCS, CCS had the highest AUC value. CCS was confirmed as the best severity correction tool. In addition, the AUC values for variables of CCS including main diagnosis, gender, age, hospitalization route, and existence of surgery were 0.808 for the logistic regression analysis, 0.785 for the decision tree, 0.809 for the neural network and 0.830 for the support vector machine. Therefore, the best predictive power was achieved by the support vector machine technique. The results of this study can be used in the establishment of health policy in the future.

• Journal of Digital Convergence
• /
• v.10 no.1
• /
• pp.413-422
• /
• 2012

In this study, we developed the severity-adjusted length of stay (LOS) model for acute myocardial infarction patients using data from the hospital discharge survey and proposed management of medical quality and development of policy. The dataset was taken from 2,309 database of the hospital discharge survey from 2004 to 2006. The severity-adjusted LOS model for the acute myocardial infarction (AMI) patients was developed by data mining analysis. From decision making tree model, the main reasons for LOS of AMI patients were CABG and comorbidity. The difference between severity-adjusted LOS from the ensemble model and real LOS was compared and it was confirmed that insurance type and location of hospital were statistically associated with LOS. And to conclude, hospitals should develop the severity-adjusted LOS model for frequent diseases to manage LOS variations efficiently and apply it into the medical information system.

• Journal of Korean Critical Care Nursing
• /
• v.5 no.2
• /
• pp.61-71
• /
• 2012

Purpose: The aim of this study was to measure the inter-rater reliability of Emergency severity index (ESI) version 4 among triage nurse. Methods: This study was carried out from August 11, 2010 to September 7, 2010 in a regional emergency department. Data collection was done by ten triage nurses who trained ESI v.4. Two research nurses and ten triage nurses scored the ESI version 4 to the patients as references, independently. We calculated the weighted kappa between the triage nurses and research nurses to evaluate the consistency of the ESI v.4. Results: A total of 233 patients were enrolled in this study. Classification of ESI level was as follows - level 1 (0.4%), level 2 (21.0%), level 3 (67.8%), level 4 (9.4%), and level 5 (1.3%). Inter-rater reliability by weighted kappa was 0.79 (95% Confidence Interval= 0.74-0.83) and agreement rate was 87.1%. Under-triage rate by triage nurse was 6.0% and over-triage rate was 6.9%. Conclusion: For this study, inter-rater reliability was measured good level between triage nurses and research nurses in Korean single ED.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.6
• /
• pp.2668-2676
• /
• 2011

In order to analyze the variation in length of stay(LOS) of injury inpatients, we developed severity-adjusted LOS model using Korean National Discharge In-depth Injury Survey data of Center for Disease Control. Appling this model, we calculated predicted values and, after standardizing LOS using the differences from the actual values, analyzed the variation in LOS. Major factors affecting severity-adjusted LOS of injury inpatients were found to be severity, surgery(or no surgery), age, injury mechanism and channel of hospitalization. Result of analysis of the differences between the actual values and predicted values adjusted by decision tree model suggested that there were statistically significant differences by hospital size(number of beds), type of insurance and location of institution. In order to reduce the variation in LOS, efforts should be exerted in developing nationwide treatment protocol, inducing medical institutions to utilize it, and furthermore systematically evaluating it to reduce the variation continually.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.12
• /
• pp.7148-7159
• /
• 2014

This study examined the relationship between the death perceptions and attitudes of the severely diseased persons in hospice facilities based on their general characteristics. The surveys were conducted from March 10 to July 31, 2013 on 149 patients at hospice facilities in ${\bigcirc}$ city, Gyeonggi-do. The data was analyzed by the SPSS WIN 18.0. First, positive death attitudes showed significant differences according to the patients' general characteristics (F=6.218, p<.001). Second, the patients' death attitudes by their death perceptions showed meaningful results (F=6.634, p<.001). Third, the death attitudes revealed a positive relation with hospice use (r=.496, p<.001). Overall, patients, who have positive death perceptions and attitudes, have high expectations for hospice use and these results support for welfare policies to encourage hospice use of severely diseased persons.

• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.221-233
• /
• 2013

This study aims to develop the severity-adjusted length of stay(LOS) model for acute stroke patients using data from the hospital discharge survey and propose management of length of stay(LOS) for acute stroke patients and using for Hospital management. The dataset was taken from 23,134 database of the hospital discharge survey from 2004 to 2009. The severity-adjusted LOS model for the acute stroke patients was developed by data mining analysis. From decision making tree model, the main reasons for LOS of acute stroke patients were acute stroke type. The difference between severity-adjusted LOS from the decision making tree model and real LOS was compared and it was confirmed that insurance type and bed number of hospital, location of hospital were statistically associated with LOS. And to conclude, hospitals should manage the LOS of acute stroke patients applying it into the medical information system.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.1
• /
• pp.175-182
• /
• 2011

This study proposes CAOPI(Computer Aided Organ Prediction Index) system based on APACHE II(Acute Physiology And Chronic Health Evaluation) for classifying disease severity and predicting the conditions of patients' major organs. The existing ICU disease severity evaluation is mostly about calculating risk scores using patients' data at certain points, which has limitations on making precise treatments. CAOPI system is designed to provide personalized treatments by classifying accurate severity degrees of emergency patients, predicting patients' mortality rate and scoring the conditions of certain organs.

• Journal of Convergence for Information Technology
• /
• v.10 no.11
• /
• pp.98-106
• /
• 2020

This study was conducted to identify the factors influencing the severity of pressure injuries of patients with pressure injuries admitted to acute university hospital. This study was a secondary analysis on the data of the study conducted to identify the factors influencing the deterioration of pressure injuries during hospitalization. The data were collected by retrospectively examining the medical records of patients with pressure injuries who were 18 years of age or older and who were admitted to acute university hospital from May 2017 to November 2018. We used data from 472 patients with pressure injuries at admission for this secondary analysis. In order to identify the factor influencing of severe pressure injuries compare to superficial pressure injuries, we analyzed the data using logistic regression analysis. As a result of the study, gender, body temperature, and patient's movement were identified as factors affecting severe pressure injuries. Therefore, special care is necessary to increased the number of position change for inpatients with pressure injuries, especially for patients with decreased mobility.

• Journal of Digital Convergence
• /
• v.13 no.5
• /
• pp.89-99
• /
• 2015

This study aims to develop a LOS(Length of Stay) bench-making system that can provide efficient by comparing the LOS management of other hospital and level evaluation for inducing the LOS to manage their own activities. The convergence LOS bench-making web program has been implemented to compare a variety of beds, regional group, followed reporting with excel files downloads by using the severity-adjusted LOS model of Korean National Hospital Discharge in-depth Injury Survey data. Features that are computed in real-time severity-adjusted LOS was also implemented. Trial operating results, bench-making system was confirmed efficient for management of LOS on the long-term care and group of disease in hospital from the staff or medical department, receive requests comparative statistics by area and disease group. Therefore the policy alternative on extension of severity-adjusted LOS is needed to utilized bench-making system on LOS.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.1-7
• /
• 2022

The study was conducted to determine the effectiveness of the triage training program utilizing pre-and post-training experiments designed for 119 emergency medical services teams. Objectives: This study evaluated the effectiveness of triage training programs on the accuracy of triage performed by 119 emergency medical services team staff who participated in the triage training program. Behavior: Participants in this study included 119 of the 166 EMS staff. In this program, a modified START triage consisting of a 20-minute theoretical presentation was presented to the participants. Data were analyzed using SPSS 21.0. Results: A significant increase in triage accuracy for 119 EMS teams(p<.001). And undertriage showed a significant decrease(p<.001). In addition, overtriage showed a decrease but was not statistically significant. Conclusions: The results obtained from this study showed that the triage training program was effective in improving the accuracy of the triage of multiple injury patients or disaster victims when presented to the 119 emergency medical services team. Therefore, these results suggest that it would be helpful to add triage training to the fire department's formal training program.