Unbalanced data can have an impact on the machine learning (ML) algorithms that build predictive models. This manuscript studies the influence of oversampling and undersampling strategies on the learning of the Bayesian classification models that predict the risk of suffering preeclampsia. Given the properties of our dataset, only the oversampling and undersampling methods that operate with numerical and categorical attributes will be taken into consideration. In particular, synthetic minority oversampling techniques for nominal and continuous data (SMOTE-NC), SMOTE—Encoded Nominal and Continuous (SMOTE-ENC), random oversampling examples (ROSE), random undersampling examples (UNDER), and random oversampling techniques (OVER) are considered. According to the results, when balancing the class in the training dataset, the accuracy percentages do not improve. However, in the test dataset, both positive and negative cases of preeclampsia were accurately classified by the models, which were built on a balanced training dataset. In contrast, models built on the imbalanced training dataset were not good at detecting positive cases of preeclampsia. We can conclude that while imbalanced training datasets can be addressed by using oversampling and undersampling techniques before building prediction models, an improvement in model accuracy is not always guaranteed. Despite this, the sensitivity and specificity percentages improve in binary classification problems in most cases, such as the one we are dealing with in this manuscript.

To improve requirement specification skills, it is vital to detect ambiguous requirements in order to correct them later. Thus, to help software engineering students improve their capacity to identify ambiguous user requirements (requirements that do not use technical words) while providing them with a valuable and engaging educational experience, the current study proposes a serious game called DEAR. It consists of a didactic exercise in which participants must move different requirements left or right to indicate whether they are ambiguous or unambiguous. To assess the improvement in students’ abilities in requirement specification and perceptions about the training class when using the DEAR game, we conducted an experiment with 62 participants, splitting them into two groups: one that used the DEAR game and the other that underwent a conventional training session. It was found that, during the training sessions, both groups became more adept at identifying unambiguous user requirements, but there was no discernible difference in performance between them. However, the game group expressed a stronger preference for the training session’s engagement and quality, as well as a stronger sense of having learned how to clearly define user requirements. Overall, the experiment shows that the suggested serious game DEAR may be a helpful teaching tool that yields learning outcomes comparable to those of a chalkboard class while encouraging students to identify unambiguous user requirements in an interactive manner.

The management of public health in a nation is a crucial matter. The emergency departments are very packed, as in many other countries. To explore in-depth the monthly number of emergency room arrivals of preeclampsia patients during the period 2019–2023 at the “IESS Hospital del Día Sur Valdivia” in Guayaquil, Ecuador, we use descriptive, diagnostic, predictive, and prescriptive (DDPP) analytics together. The descriptive phase considered the benefits of statistics for data characterization. The diagnostic phase is in which the relationships of the trend, seasonality, stationarity, autocorrelation, and anomalies of the time series are reviewed. The predictive phase uses deep learning and statistical models to predict emergency arrivals. The multilayer perceptron model (MLP) achieved the best performance (a mean absolute percentage error of 17.21%), selecting it to forecast the number of preeclamptic emergencies during 2024. Finally, in the prescriptive phase, possible solutions are analyzed using two scenarios presented. The results show each phase of the DDPP analyzes, providing valuable information to improve hospital management. This work can serve as a basis for future studies on the joint application of all DDPP analyses to univariate time series, providing a step-by-step guide on how to analyze such data and introducing a systematic procedure for their analysis for those who may lack statistical expertise.