To improve and keep the competitiveness, it is necessary to keep pace with available changes in technology, and it is essential to establish the flexible and accurate information system about the disease. And for the accurate decision-making, target setting and prediction of movement, the estimating of the short- and long-term effects of the strategies of disease related service are required. But the limited informations, including all of knowledge of leprosy, make it difficult to estimate them properly. To achieve the more effective leprosy related service, we have to make the effort to crate the more accurate system. To proffer the idea for the development of information monitoring, we present the reviews of some articles about the information theories that used the leprosy related service.
Information Systems ; Information Theory ; Leprosy*

OBJECTIVE: The purpose of this study was to explore the usability of a feature selection method based on the mutual information theory to increase predictive performance of a classifier in data mining. METHODS: The HIV Cost and Services Utilization Study(HCSUS) dataset was used to apply the feature selection method to a classifier. Its contribution to increasing the predictive performance of the classifier was evaluated by comparing the Naive Bayes(NB) and the Logistic Regression(LG) models using different variables. The infrequent office visit representing limited health service utilization was selected as an outcome variable. HUGIN Researcher(TM) 6.3 was used to train and test the NB models and SAS(R) 8.0 was used for the LG modeling. RESULTS: Higher AUC in the NB model was obtained using the variables selected by the mutual information based feature selection method(AUC=.639, CI=.611, .660); lower AUC using the variables defined by a previous study(AUC=.599, CI=.570, .620). There was no difference between the LG models with different variables. CONCLUSION: This study demonstrated the mutual information method may be useful in identifying relevant predictors as the feature selection method, which can contribute to an increase in the predictive performance of a classifier.
Area Under Curve ; Data Mining ; Dataset ; Health Services ; HIV ; Information Theory* ; Office Visits

BACKGROUND: The prostate-specific antigen (PSA) is considered the most useful among tumor markers currently used. However, its quantitative results are interpreted only qualitatively for the diagnosis of prostate cancer. The recently introduced information theory enables the information of the quantitative results transformed into Shannon's entropy (S) that represents uncertainties and then "1-S" representing diagnostic certainty. METHODS: The 882 urological patients enrolled were categorized into 2 groups: a patient group comprising 233 patients with prostate cancer and a disease control group comprising 649 patients with benign prostate disease. The level of PSA in all the patients was tested and was found to be > or =2 ng/mL. The variables like PSA level and age were modeled on logistic regression analysis to predict the probability of prostate cancer and the diagnostic certainty. RESULTS: The mean (SD) of PSA levels in the patient group and the disease control group were 44.5 ng/mL (37.62 ng/mL) and 5.7 ng/mL (3.70 ng/mL), respectively. The logistic regression model fitted well when the age variable was dichotomized at the age of 55 yr. The diagnostic certainty was lowest at a PSA level of 18.90 ng/mL in the <55-yr age group, and 15.45 ng/mL in the >55-yr age group. CONCLUSIONS: The diagnostic certainty (1-S) of whether to diagnose prostate cancer or not at a certain PSA level could be obtained using the information theory. The methodology used in this study may help interpret the results of other quantitative tests.
Age Factors ; Aged ; Entropy ; Humans ; *Information Theory ; Logistic Models ; Male ; Middle Aged ; Prostate-Specific Antigen/*blood ; Prostatic Diseases/diagnosis ; Prostatic Neoplasms/*diagnosis

PURPOSE: This study was done to examine the level of use of essential oriental nursing terms and related characteristics among nurses in oriental medicine (OM) hospitals. METHOD: A cross-sectional survey design with convenience sampling was employed. Questionnaires were used to collect data from 315 nurses in seven university-affiliated OM hospitals. The questionnaire included 174 oriental nursing terms about actions, tests, drugs, and theories. Multiple regression analysis was performed to determine factors associated with the level of use. RESULTS: The response rate was 98.1% (n=309). Overall mean score for use of essential oriental nursing terms was 2.7(+/-0.7) on a five-point Likert scale. Significant factors associated with the level of use were workplace and knowledge of oriental nursing theory terms. Nurses who worked in nursing care wards and those who had a higher level of knowledge of oriental nursing theories had a higher level of use. CONCLUSIONS: These findings indicate that level of use of essential oriental nursing terms were below average. Educational programs to enhance knowledge of oriental nursing theories need to be implemented for nurses in OM hospitals, considering their workplace, in order to facilitate nursing data sharing and communication among healthcare providers.
Cross-Sectional Studies ; Health Personnel ; Humans ; Information Dissemination ; Medicine, East Asian Traditional ; Medicine, Korean Traditional ; Nursing Care ; Nursing Theory ; Surveys and Questionnaires