• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.1019-1032
• /
• 2013

The accurate prediction of future mortality is an important issue due to recent rapid increases in life expectancy. An accurate estimation and prediction of mortality is important to future welfare policies. The optimal selection of a mortality model is important to estimate and predict mortality; however, the period of time series data used is also an important issue. It is essential to understand that the time series data for mortality is short in Korea and the data before 1982 is incomplete. This paper divides the time series of Korean mortality into two sets to compare the parameter estimates of the LC model and LC model with a cohort effect by the period of data used. A modeling and prediction of the mortality index and cohort effect index as well as the evaluation of future life expectancy is conducted. Finally, some suggestions are proposed for the future prediction of mortality.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.309-316
• /
• 2020

We predict the mortality of the elderly patients visiting the emergency department who are over 65 years old using Feed Forward Neural Network (FFNN) and Convolutional Neural Network (CNN) respectively. Medical data consist of 99 features including basic information such as sex, age, temperature, and heart rate as well as past history, various blood tests and culture tests, and etc. Among these, we used random forest to select features by measuring the importance of features in the prediction of mortality. As a result, using the top 80 features with high importance is best in the mortality prediction. The performance of the FFNN and CNN is compared by using the selected features for training each neural network. To train CNN with images, we convert medical data to fixed size images. We acquire better results with CNN than with FFNN. With CNN for mortality prediction, F1 score and the AUC for test data are 56.9 and 92.1 respectively.

• Journal of Chest Surgery
• /
• v.54 no.2
• /
• pp.88-98
• /
• 2021

Background: This study aimed to develop a new risk prediction model for operative mortality in a Korean cohort undergoing heart valve surgery using the Korea Heart Valve Surgery Registry (KHVSR) database. Methods: We analyzed data from 4,742 patients registered in the KHVSR who underwent heart valve surgery at 9 institutions between 2017 and 2018. A risk prediction model was developed for operative mortality, defined as death within 30 days after surgery or during the same hospitalization. A statistical model was generated with a scoring system by multiple logistic regression analyses. The performance of the model was evaluated by its discrimination and calibration abilities. Results: Operative mortality occurred in 142 patients. The final regression models identified 13 risk variables. The risk prediction model showed good discrimination, with a c-statistic of 0.805 and calibration with Hosmer-Lemeshow goodness-of-fit p-value of 0.630. The risk scores ranged from -1 to 15, and were associated with an increase in predicted mortality. The predicted mortality across the risk scores ranged from 0.3% to 80.6%. Conclusion: This risk prediction model using a scoring system specific to heart valve surgery was developed from the KHVSR database. The risk prediction model showed that operative mortality could be predicted well in a Korean cohort.

• Journal of the Korean Burn Society
• /
• v.23 no.1
• /
• pp.1-6
• /
• 2020

Purpose: PL, creatinine and urine output are biomarkers of the suitability and prognosis of fluid therapy in severe burn patients. The purpose of this study is to evaluate the usefulness of predicting mortality by biomarkers and its change during initial fluid therapy for severe burn patients. Methods: A retrograde review was performed on 733 patients from January 2014 to December 2018 who were admitted as severe burn patients to our burn intensive care unit (BICU). Plasma lactate, serum creatinine and urine output were measured at the time of admission to the BICU and after 48 hours. ABSI score, Hangang score, APACHEII, revised Baux index and TBSA were collected after admission. Results: 733 patients were enrolled. PL was the most useful indicators for predicting mortality in burn patients at the time of admission (AUC: 0.813) and after 48 hours (AUC: 0.698). On the other hand, mortality prediction from initial fluid therapy for 48 hours showed different results. Only creatinine showed statistical differences (P<0.05) in mortality prediction. But there were no statistical differences in mortality prediction with PL and UO (P>0.05). Conclusion: In this study, PL was most useful predictor among biomarkers for predicting mortality. Improvement in creatinine levels during the first 48 hours is associated with improved mortality. Therefore, efforts are needed to improve creatinine levels.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.16
• /
• pp.6929-6934
• /
• 2014

Background: To analyze the mortality distribution of esophageal cancer in China from 1991 to 2012, to forecast the mortality in the future five years, and to provide evidence for prevention and treatment of esophageal cancer. Materials and Methods: Mortality data for esophageal cancer in China from 1991 to 2012 were used to describe its epidemiological characteristics, such as the change of the standardized mortality rate, urban-rural differences, sex and age differences. Trend-surface analysis was used to study the geographical distribution of the mortality. Curve estimation, time series, gray modeling, and joinpoint regression were used to predict the mortality for the next five years in the future. Results: In China, the incidence rate of esophageal cancer from 2007 and the mortality rate of esophageal cancer from 2008 increased yearly, with males at $8.72/10^5$ being higher than females, and the countryside at $15.5/10^5$ being higher than in the city. The mortality rate increased from age 45. Geographical analysis showed the mortality rate increased from southern to eastern China, and from northeast to central China. Conclusions: The incidence rate and the standardized mortality rate of esophageal cancer are rising. The regional disease control for esophageal cancer should be focused on eastern, central and northern regions China, and the key targets for prevention and treatment are rural men more than 45 years old. The mortality of esophageal cancer will rise in the next five years.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.15
• /
• pp.6729-6734
• /
• 2015

Background: To analyze the mortality distribution of nasopharyngeal carcinoma in China from 1991 to 2013, to predict the mortality in the ensuing five years, and to provide evidence for prevention and treatment of nasopharyngeal carcinoma. Materials and Methods: Mortality data for Nasopharyngeal Carcinoma in China from 1991 to 2013 were used to describe its epidemiological characteristics, such as the change of the standardized mortality rate, sex and age differences, urban-rural differences. Trend-surface analysis was used to study the geographical distribution of the mortality. Curve estimation, time series, gray modeling, and joinpoint regression were used to predict the mortality for the ensuing five years in the future. Results: In China, the standardized mortality rate of Nasopharyngeal Carcinoma increased with time from 1996, reaching the peak values of $1.45/10^5$ at the year of 2002, and decreased gradually afterwards. With males being 1.51 times higher than females, and the city had a higher rate than the rural during the past two decades. The mortality rate increased from age 40. Geographical analysis showed the mortality rate increased from middle to southern China. Conclusions: The standardized mortality rate of Nasopharyngeal Carcinoma is falling. The regional disease control for Nasopharyngeal Carcinoma should be focused on Guangdong province of China, and the key targets for prevention and treatment are rural men, especially after the age of 40. The mortality of Nasopharyngeal Carcinoma will decrease in the next five years.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.7
• /
• pp.275-280
• /
• 2018

As the global population becomes aging, the demand for health services for the elderly is expected to increase. In particular, The elderly visiting the emergency department sometimes have complex medical, social, and physical problems, such as having a variety of illnesses or complaints of unusual symptoms. The proposed system is designed to predict the mortality of the elderly patients who are over 65 years old and have admitted the emergency department. For mortality prediction, we compare the support vector machines and Feed Forward Neural Network (FFNN) trained with medical data such as age, sex, blood pressure, body temperature, etc. The results of the FFNN with a hidden layer are best in the mortality prediction, and F1 score and the AUC is 52.0%, 88.6% respectively. If we improve the performance of the proposed system by extracting better medical features, we will be able to provide better medical services through an effective and quick allocation of medical resources for the elderly patients visiting the emergency department.

• Journal of The Korean Society of Emergency Medicine
• /
• v.29 no.5
• /
• pp.455-464
• /
• 2018

Objective: Machine learning is not yet widely used in the medical field. Therefore, this study was conducted to compare the performance of preexisting severity prediction models and machine learning based models (random forest [RF], gradient boosting [GB]) for mortality prediction in pneumonia patients. Methods: We retrospectively collected data from patients who visited the emergency department of a tertiary training hospital in Seoul, Korea from January to March of 2015. The Pneumonia Severity Index (PSI) and Sequential Organ Failure Assessment (SOFA) scores were calculated for both groups and the area under the curve (AUC) for mortality prediction was computed. For the RF and GB models, data were divided into a test set and a validation set by the random split method. The training set was learned in RF and GB models and the AUC was obtained from the validation set. The mean AUC was compared with the other two AUCs. Results: Of the 536 investigated patients, 395 were enrolled and 41 of them died. The AUC values of PSI and SOFA scores were 0.799 (0.737-0.862) and 0.865 (0.811-0.918), respectively. The mean AUC values obtained by the RF and GB models were 0.928 (0.899-0.957) and 0.919 (0.886-0.952), respectively. There were significant differences between preexisting severity prediction models and machine learning based models (P<0.001). Conclusion: Classification through machine learning may help predict the mortality of pneumonia patients visiting the emergency department.

• Journal of Korean Society of Forest Science
• /
• v.100 no.1
• /
• pp.1-7
• /
• 2011

The objective of this study was to improve the performance of the existing individual-tree/distantindependent stand growth model in predicting the growth of Pinus koraiensis forest stands. The parameters of diameter growth and mortality prediction models were estimated using periodic annual increment (PAI) of permanent plots and the performance of the models were compared with that of the existing ones using mean anuual increment (MAI). The diameter growth model includes crown ratio, potential diameter growth and modifier to compute for competitions of trees of a stand. In deriving the mortality prediction model, the parameters were estimated based on PAI which was also estimated as the function of MAI due to the lacking of permanent plot data. The results of this study showed that the newly-estimated functions based on PAI provide more realistic patterns in diameter growth of individual trees. The new approach using PAI in mortality model seems to overcome the over-estimate problem by the MAI-based model in estimating mortality of stand trees.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.6
• /
• pp.2785-2791
• /
• 2014

Aims: To analyze time-dependent changes in female breast cancer (BC) mortality in China, forecast the trend in the ensuing 5 years, and provide recommendations for prevention and management. Materials and Methods: Mortality data of breast cancer in China from 1991 to 2011 was used to describe characteristics and distribution, such as the changes of the standardized mortality rate, urban-rural differences and age differences. Trend-surface analysis was used to study the geographical distribution of mortality. In addition, curve estimation, time series modeling, Gray modeling (GM) and joinpoint regression were performed to estimate and predict future trends. Results: In China, the mortality rate of breast cancer has increased yearly since 1991. In addition, our data predicted that the trend will continue to increase in the ensuing 5 years. Rates in urban areas are higher than those in rural areas. Over the past decade, all peak ages for death by breast cancer have been delayed, with the first death peak occurring at 55 to 65 years of age in urban and rural areas. Geographical analysis indicated that mortality rates increased from Southwest to Northeast and from West to East. Conclusions: The standardized mortality rate of breast cancer in China is rising and the upward trend is predicted to continue for the next 5 years. Since this can cause an enormous health impact in China, much better prevention and management of breast cancer is needed. Consequently, disease control centers in China should place more focus on the northeastern, eastern and southeastern parts of China for breast cancer prevention and management, and the key population should be among women between ages 55 to 65, especially those in urban communities.