The high incidence and prevalence of chronic kidney disease (CKD), often caused by late diagnoses, is a critical public health problem, especially in developing countries such as Brazil. CKD treatment therapies, such as dialysis and kidney transplantation, increase the morbidity and mortality rates, besides the public health costs. This study analyses the usage of machine learning techniques to assist in the early diagnosis of CKD in developing countries. Qualitative and quantitative comparative analyses are, respectively, conducted using a systematic literature review and an experiment with machine learning techniques, with the k-fold cross-validation method based on the Weka© software and a CKD dataset. These analyses enable a discussion on the suitability of machine learning techniques for screening for CKD risk, focusing on low-income and hard-to-reach settings of developing countries, due to the specific problems faced by them, e.g., inadequate primary health care. The study results show that the J48 decision tree is a suitable machine learning technique for such screening in developing countries, due to the easy interpretation of its classification results, with 95.00% accuracy, reaching a nearly perfect agreement with an experienced nephrologist‘s opinion. Conversely, random forest, naive Bayes, support vector machine, multilayer perceptron, and k-nearest neighbor techniques, respectively, yield 93.33%, 88.33%, 76.66%, 75.00%, and 71.67% accuracy, presenting at least moderate agreement with the nephrologist, at the cost of a more difficult interpretation of the classification results.

Chronic kidney disease (CKD) is a worldwide public health problem, usually diagnosed in the late stages of the disease. To alleviate such issue, investment in early prediction is necessary. The purpose of this study is to assist the early prediction of CKD, addressing problems related to imbalanced and limited-size datasets. We used data from medical records of Brazilians with or without a diagnosis of CKD, containing the following attributes: hypertension, diabetes mellitus, creatinine, urea, albuminuria, age, gender, and glomerular filtration rate. We present an oversampling approach based on manual and automated augmentation. We experimented with the synthetic minority oversampling technique (SMOTE), Borderline-SMOTE, and Borderline-SMOTE SVM. We implemented models based on the algorithms: decision tree (DT), random forest, and multi-class AdaBoosted DTs. We also applied the overall local accuracy and local class accuracy methods for dynamic classifier selection; and the k-nearest oracles-union, k-nearest oracles-eliminate, and META-DES for dynamic ensemble selection. We analyzed the models’ performances using the hold-out validation, multiple stratified cross-validation (CV), and nested CV. The DT model presented the highest accuracy score (98.99%) using the manual augmentation and SMOTE. Our approach can assist in designing systems for the early prediction of CKD using imbalanced and limited-size datasets.

In this paper, we outline the importance of discussion fora for e-learning applications. Due to a weak structure or size of the discussion forum, recommendations are required in order to help learners finding relevant information within a forum. We present a generic personalization framework and evaluate the framework based on a recommender architecture for the e-learning focused discussion forum Comtella-D. In the evaluation, we examine different sources of user feedback and the required amount of user interaction to provide recommendations. The outcomes of the evaluation serve as source for a personalization rule, which selects the most appropriate recommendation strategy based on available user input data. We furthermore conclude that collaborative filtering techniques can be utilize successfully in small data sets, like e-learning related discussion fora.