• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.435-447
• /
• 2019

In order to prevent unnecessary re-admission, it is necessary to intensively manage the groups with high probability of re-admission. For this, it is necessary to develop a re-admission prediction model. Two - year discharge summary data of one university hospital were collected from 2016 to 2017 to develop a predictive model of re-admission. In this case, the re-admitted patients were defined as those who were discharged more than once during the study period. We conducted descriptive statistics and crosstab analysis to identify the characteristics of rehospitalized patients. The re-admission prediction model was developed using logistic regression, neural network, and decision tree. AUC (Area Under Curve) was used for model evaluation. The logistic regression model was selected as the final re-admission predictive model because the AUC was the best at 0.81. The main variables affecting the selected rehospitalization in the logistic regression model were Residental regions, Age, CCS, Charlson Index Score, Discharge Dept., Via ER, LOS, Operation, Sex, Total payment, and Insurance. The model developed in this study was limited to generalization because it was two years data of one hospital. It is necessary to develop a model that can collect and generalize long-term data from various hospitals in the future. Furthermore, it is necessary to develop a model that can predict the re-admission that was not planned.

• Neurospine
• /
• v.15 no.4
• /
• pp.329-337
• /
• 2018

Objective: Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods: Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results: A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion: ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• The Journal of Industrial Distribution & Business
• /
• v.11 no.7
• /
• pp.29-40
• /
• 2020

Purpose: In modern society, many urban problems are occurring, such as aging, hollowing out old city centers and polarization within cities. In this study, we intend to apply big data and machine learning methodologies to predict depression symptoms in the elderly population early on, thus contributing to solving the problem of elderly depression. Research design, data and methodology: Machine learning techniques used random forest and analyzed the correlation between CES-D10 and other variables, which are widely used worldwide, to estimate important variables. Dependent variables were set up as two variables that distinguish normal/depression from moderate/severe depression, and a total of 106 independent variables were included, including subjective health conditions, cognitive abilities, and daily life quality surveys, as well as the objective characteristics of the elderly as well as the subjective health, health, employment, household background, income, consumption, assets, subjective expectations, and quality of life surveys. Results: Studies have shown that satisfaction with residential areas and quality of life and cognitive ability scores have important effects in classifying elderly depression, satisfaction with living quality and economic conditions, and number of outpatient care in living areas and clinics have been important variables. In addition, the results of a random forest performance evaluation, the accuracy of classification model that classify whether elderly depression or not was 86.3%, the sensitivity 79.5%, and the specificity 93.3%. And the accuracy of classification model the degree of elderly depression was 86.1%, sensitivity 93.9% and specificity 74.7%. Conclusions: In this study, the important variables of the estimated predictive model were identified using the random forest technique and the study was conducted with a focus on the predictive performance itself. Although there are limitations in research, such as the lack of clear criteria for the classification of depression levels and the failure to reflect variables other than KLoSA data, it is expected that if additional variables are secured in the future and high-performance predictive models are estimated and utilized through various machine learning techniques, it will be able to consider ways to improve the quality of life of senior citizens through early detection of depression and thus help them make public policy decisions.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.771-780
• /
• 2009

Cataract is the main cause of blindness and visual impairment, especially, age-related cataract accounts for about half of the 32 million cases of blindness worldwide. As the life expectancy and the expansion of the elderly population are increasing, the cases of cataract increase as well, which causes a serious economic and social problem throughout the country. However, the incidence of cataract can be reduced dramatically through early diagnosis and prevention. In this study, we developed a prediction model of cataracts for early diagnosis using hospital data of 3,237 subjects who received the screening test first and then later visited medical center for cataract check-ups cataract between 1994 and 2005. To develop the prediction model, we used random forests and compared the predictive performance of this model with other common discriminant models such as logistic regression, discriminant model, decision tree, naive Bayes, and two popular ensemble model, bagging and arcing. The accuracy of random forests was 67.16%, sensitivity was 72.28%, and main factors included in this model were age, diabetes, WBC, platelet, triglyceride, BMI and so on. The results showed that it could predict about 70% of cataract existence by screening test without any information from direct eye examination by ophthalmologist. We expect that our model may contribute to diagnose cataract and help preventing cataract in early stages.

• 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.

• Korean Journal of Radiology
• /
• v.23 no.12
• /
• pp.1281-1289
• /
• 2022

Objective: Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. Materials and Methods: A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. Results: The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Conclusion: Radiomic models using MRI were able to differentiate JME from HCs.

• Journal of Convergence for Information Technology
• /
• v.7 no.1
• /
• pp.55-60
• /
• 2017

In order to provide intelligent services without human intervention in the Internet of Things environment, it is necessary to analyze the big data generated by the IoT device and learn the normal pattern, and to predict the abnormal symptoms such as faulty or malfunction based on the learned normal pattern. The purpose of this study is to implement a machine learning model that can predict product failure by analyzing big data generated in various devices of product process. The machine learning model uses the big data analysis tool R because it needs to analyze based on existing data with a large volume. The data collected in the product process include the information about product faulty, so supervised learning model is used. As a result of the study, I classify the variables and variable conditions affecting the product failure, and proposed a prediction model for the product failure based on the decision tree. In addition, the predictive power of the model was significantly higher in the conformity and performance evaluation analysis of the model using the ROC curve.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.9
• /
• pp.89-96
• /
• 2016

According to the promoting policy for bicycle riding, the bicycle road infrastructure in Korea has been widely established. As the number of bicycle rider increases, bicycle traffic accidents also increase year after year. In this paper, we analyze bicycle traffic accident data from 2007 to 2014 which is provided by Road Traffic Authority and present statistical results of bicycle traffic accidents. And also regression analysis is applied to predict the number of daily traffic accidents in Seoul using ASOS(Automated Synoptic Observing System) climate data observed in the Seoul sector which are provided by Korea Meteorological Administration. In addition, decision tree analysis techniques are used to forecast the level of traffic accidents severity. In the analytic results of this research, we expect that it will be helpful to establish the collective policy of bicycle accident data and protective strategy in order to reduce the number of bicycle accidents.

• Journal of the Korea Convergence Society
• /
• v.9 no.10
• /
• pp.243-248
• /
• 2018

The social activities of the elderly are important in successfully achieving aging by providing opportunities for social interaction to enhance life satisfaction. The purpose of this study is to identify the related factors of the elderly social activities and build a statistical classification model to predict social activities. Subjects were 1,864 elderly people (829 males, 1,035 females) who completed the community health survey in 2015. Outcome variables were defined as the experience of social activity during the past month(yes, no). The prediction model was constructed using decision tree model based on Classification and Regression Trees (CRT) algorithm. The results of this study were subjective health, frequency of meeting with neighbors, frequency of meeting with relatives, and living with spouse were significant variables of social participation. The most prevalent predictor was the subjective health level. In order to prepare for the successful aging of the super aged society based on the results of this study, social attention and support for the social activities of the elderly are required.