Use of the mini nutritional assessment tool in elderly people from long-term institutions of southeast of Brazil

Background: the Mini Nutritional Assessment (MNA) is a multidimensional method of nutritional evaluation that allows the diagnosis of malnutrition and risk of malnutrition in elderly people, it is important to mention that this method has not been well studied in Brazil. Objective: to verify the use of the MNA in elderly people that has been living in long term institutions for elderly people. Design: transversal study. Participants: 89 people (>= 60 years), being 64.0% men. The average of age for both genders was 73.7 +/- 9.1 years old, being 72.8 +/- 8.9 years old for men, and 75.3 +/- 9.3 years old for women. Setting: long-term institutions for elderly people located in the Southeast of Brazil. Methods: it was calculated the sensibility, specificity, and positive and negative predictive values. It was data to set up a ROC curve to verify the accuracy of the MNA. The variable used as a ""standard"" for the nutritional diagnosis of the elderly people was the corrected arm muscle area because it is able to provide information or an estimative of the muscle reserve of a person being considered a good indicator of malnutrition in elderly people. Results: the sensibility was 84.0%, the specificity was 36.0%, the positive predictive value was 77.0%, and the negative predictive value was 47.0%; the area of the ROC curve was 0.71 (71.0%). Conclusion: the MNA method has showed accuracy, and sensibility when dealing with the diagnosis of malnutrition and risk of malnutrition in institutionalized elderly groups of the Southeastern region of Brazil, however, it presented a low specificity.

Poly-bagging predictors for classification modelling for credit scoring

Credit scoring modelling comprises one of the leading formal tools for supporting the granting of credit. Its core objective consists of the generation of a score by means of which potential clients can be listed in the order of the probability of default. A critical factor is whether a credit scoring model is accurate enough in order to provide correct classification of the client as a good or bad payer. In this context the concept of bootstraping aggregating (bagging) arises. The basic idea is to generate multiple classifiers by obtaining the predicted values from the fitted models to several replicated datasets and then combining them into a single predictive classification in order to improve the classification accuracy. In this paper we propose a new bagging-type variant procedure, which we call poly-bagging, consisting of combining predictors over a succession of resamplings. The study is derived by credit scoring modelling. The proposed poly-bagging procedure was applied to some different artificial datasets and to a real granting of credit dataset up to three successions of resamplings. We observed better classification accuracy for the two-bagged and the three-bagged models for all considered setups. These results lead to a strong indication that the poly-bagging approach may promote improvement on the modelling performance measures, while keeping a flexible and straightforward bagging-type structure easy to implement. (C) 2011 Elsevier Ltd. All rights reserved.