Development and application of prediction model of hyperlipidemia using SVM and meta-learning algorithm (SVM과 meta-learning algorithm을 이용한 고지혈증 유병 예측모형 개발과 활용)
-
- 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.
Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.
Fuzzy logic based Control Theory has gained much interest in the industrial world, thanks to its ability to formalize and solve in a very natural way many problems that are very difficult to quantify at an analytical level. This paper shows a solution for treating membership function inside hardware circuits. The proposed hardware structure optimizes the memoried size by using particular form of the vectorial representation. The process of memorizing fuzzy sets, i.e. their membership function, has always been one of the more problematic issues for the hardware implementation, due to the quite large memory space that is needed. To simplify such an implementation, it is commonly [1,2,8,9,10,11] used to limit the membership functions either to those having triangular or trapezoidal shape, or pre-definite shape. These kinds of functions are able to cover a large spectrum of applications with a limited usage of memory, since they can be memorized by specifying very few parameters ( ight, base, critical points, etc.). This however results in a loss of computational power due to computation on the medium points. A solution to this problem is obtained by discretizing the universe of discourse U, i.e. by fixing a finite number of points and memorizing the value of the membership functions on such points [3,10,14,15]. Such a solution provides a satisfying computational speed, a very high precision of definitions and gives the users the opportunity to choose membership functions of any shape. However, a significant memory waste can as well be registered. It is indeed possible that for each of the given fuzzy sets many elements of the universe of discourse have a membership value equal to zero. It has also been noticed that almost in all cases common points among fuzzy sets, i.e. points with non null membership values are very few. More specifically, in many applications, for each element u of U, there exists at most three fuzzy sets for which the membership value is ot null [3,5,6,7,12,13]. Our proposal is based on such hypotheses. Moreover, we use a technique that even though it does not restrict the shapes of membership functions, it reduces strongly the computational time for the membership values and optimizes the function memorization. In figure 1 it is represented a term set whose characteristics are common for fuzzy controllers and to which we will refer in the following. The above term set has a universe of discourse with 128 elements (so to have a good resolution), 8 fuzzy sets that describe the term set, 32 levels of discretization for the membership values. Clearly, the number of bits necessary for the given specifications are 5 for 32 truth levels, 3 for 8 membership functions and 7 for 128 levels of resolution. The memory depth is given by the dimension of the universe of the discourse (128 in our case) and it will be represented by the memory rows. The length of a world of memory is defined by: Length = nem (dm(m)＋dm(fm) Where: fm is the maximum number of non null values in every element of the universe of the discourse, dm(m) is the dimension of the values of the membership function m, dm(fm) is the dimension of the word to represent the index of the highest membership function. In our case then Length=24. The memory dimension is therefore 128*24 bits. If we had chosen to memorize all values of the membership functions we would have needed to memorize on each memory row the membership value of each element. Fuzzy sets word dimension is 8*5 bits. Therefore, the dimension of the memory would have been 128*40 bits. Coherently with our hypothesis, in fig. 1 each element of universe of the discourse has a non null membership value on at most three fuzzy sets. Focusing on the elements 32,64,96 of the universe of discourse, they will be memorized as follows: The computation of the rule weights is done by comparing those bits that represent the index of the membership function, with the word of the program memor . The output bus of the Program Memory (μCOD), is given as input a comparator (Combinatory Net). If the index is equal to the bus value then one of the non null weight derives from the rule and it is produced as output, otherwise the output is zero (fig. 2). It is clear, that the memory dimension of the antecedent is in this way reduced since only non null values are memorized. Moreover, the time performance of the system is equivalent to the performance of a system using vectorial memorization of all weights. The dimensioning of the word is influenced by some parameters of the input variable. The most important parameter is the maximum number membership functions (nfm) having a non null value in each element of the universe of discourse. From our study in the field of fuzzy system, we see that typically nfm 3 and there are at most 16 membership function. At any rate, such a value can be increased up to the physical dimensional limit of the antecedent memory. A less important role n the optimization process of the word dimension is played by the number of membership functions defined for each linguistic term. The table below shows the request word dimension as a function of such parameters and compares our proposed method with the method of vectorial memorization[10]. Summing up, the characteristics of our method are: Users are not restricted to membership functions with specific shapes. The number of the fuzzy sets and the resolution of the vertical axis have a very small influence in increasing memory space. Weight computations are done by combinatorial network and therefore the time performance of the system is equivalent to the one of the vectorial method. The number of non null membership values on any element of the universe of discourse is limited. Such a constraint is usually non very restrictive since many controllers obtain a good precision with only three non null weights. The method here briefly described has been adopted by our group in the design of an optimized version of the coprocessor described in [10].
This project was a service-cum-research effort with a quasi-experimental study design to examine the health benefits of an integrated Family Planning (FP)/Maternal & Child health (MCH) Service approach that provides crucial factors missing in the present on-going programs. The specific objectives were: 1) To test the effectiveness of trained nurse/midwives (MW) assigned as change agents in the Health Sub-Center (HSC) to bring about the changes in the eight FP/MCH indicators, namely; (i)FP/MCH contacts between field workers and their clients (ii) the use of effective FP methods, (iii) the inter-birth interval and/or open interval, (iv) prenatal care by medically qualified personnel, (v) medically supervised deliveries, (vi) the rate of induced abortion, (vii) maternal and infant morbidity, and (viii) preinatal & infant mortality. 2) To measure the integrative linkage (contacts) between MW & HSC workers and between HSC and clients. 3) To examine the organizational or administrative factors influencing integrative linkage between health workers. Study design; The above objectives called for quasi-experimental design setting up a study and control area with and without a midwife. An active intervention program (FP/MCH minimum 'package' program) was conducted for a 2 year period from June 1982-July 1984 in Seosan County and 'before and after' surveys were conducted to measure the change. Service input; This study was undertaken by the Soonchunhyang University in collaboration with WHO. After a baseline survery in 1981, trained nurses/midwives were introduced into two health sub-centers in a rural setting (Seosan county) for a 2 year period from 1982 to 1984. A major service input was the establishment of midwifery services in the existing health delivery system with emphasis on nurse/midwife's role as the link between health workers (nurse aids) and village health workers, and the referral of risk patients to the private physician (OBGY specialist). An evaluation survey was made in August 1984 to assess the effectiveness of this alternative integrated approach in the study areas in comparison with the control area which had normal government services. Method of evaluation; a. In this study, the primary objective was first to examine to what extent the FP/MCH package program brought about changes in the pre-determined eight indicators (outcome and impact measures) and the following relationship was first analyzed; b. Nevertheless, this project did not automatically accept the assumption that if two or more activities were integrated, the results would automatically be better than a non-integrated or categorical program. There is a need to assess the 'integration process' itself within the package program. The process of integration was measured in terms of interactive linkages, or the quantity & quality of contacts between workers & clients and among workers. Intergrative linkages were hypothesized to be influenced by organizational factors at the HSC clinic level including HSC goals, sltrurture, authority, leadership style, resources, and personal characteristics of HSC staff. The extent or degree of integration, as measured by the intensity of integrative linkages, was in turn presumed to influence programme performance. Thus as indicated diagrammatically below, organizational factors constituted the independent variables, integration as the intervening variable and programme performance with respect to family planning and health services as the dependent variable: Concerning organizational factors, however, due to the limited number of HSCs (2 in the study area and 3 in the control area), they were studied by participatory observation of an anthropologist who was independent of the project. In this observation, we examined whether the assumed integration process actually occurred or not. If not, what were the constraints in producing an effective integration process. Summary of Findings; A) Program effects and impact 1. Effects on FP use: During this 2 year action period, FP acceptance increased from 58% in 1981 to 78% in 1984 in both the study and control areas. This increase in both areas was mainly due to the new family planning campaign driven by the Government for the same study period. Therefore, there was no increment of FP acceptance rate due to additional input of MW to the on-going FP program. But in the study area, quality aspects of FP were somewhat improved, having a better continuation rate of IUDs & pills and more use of effective Contraceptive methods in comparison with the control area. 2. Effects of use of MCH services: Between the study and control areas, however, there was a significant difference in maternal and child health care. For example, the coverage of prenatal care was increased from 53% for 1981 birth cohort to 75% for 1984 birth cohort in the study area. In the control area, the same increased from 41% (1981) to 65% (1984). It is noteworthy that almost two thirds of the recent birth cohort received prenatal care even in the control area, indicating that there is a growing demand of MCH care as the size of family norm becomes smaller 3. There has been a substantive increase in delivery care by medical professions in the study area, with an annual increase rate of 10% due to midwives input in the study areas. The project had about two times greater effect on postnatal care (68% vs. 33%) at delivery care(45.2% vs. 26.1%). 4. The study area had better reproductive efficiency (wanted pregancies with FP practice & healthy live births survived by one year old) than the control area, especially among women under 30 (14.1% vs. 9.6%). The proportion of women who preferred the 1st trimester for their first prenatal care rose significantly in the study area as compared to the control area (24% vs 13%). B) Effects on Interactive Linkage 1. This project made a contribution in making several useful steps in the direction of service integration, namely; i) The health workers have become familiar with procedures on how to work together with each other (especially with a midwife) in carrying out their work in FP/MCH and, ii) The health workers have gotten a feeling of the usefulness of family health records (statistical integration) in identifying targets in their own work and their usefulness in caring for family health. 2. On the other hand, because of a lack of required organizational factors, complete linkage was not obtained as the project intended. i) In regards to the government health worker's activities in terms of home visiting there was not much difference between the study & control areas though the MW did more home visiting than Government health workers. ii) In assessing the service performance of MW & health workers, the midwives balanced their workload between 40% FP, 40% MCH & 20% other activities (mainly immunization). However,