While preeclampsia is the leading cause of maternal death in Guayas province (Ecuador), its causes have not yet been studied in depth. The objective of this research is to build a Bayesian network classifier to diagnose cases of preeclampsia while facilitating the understanding of the causes that generate this disease. Data for the years 2017 through 2023 were gathered retrospectively from medical histories of patients treated at “IESS Los Ceibos” hospital in Guayaquil, Ecuador. Naïve Bayes (NB), The Chow–Liu Tree-Augmented Naïve Bayes (${\mathrm{TAN}}_{cl}$), and Semi Naïve Bayes (FSSJ) algorithms have been considered for building explainable classification models. A proposed Non-Redundant Feature Selection approach (NoReFS) is proposed to perform the feature selection task. The model trained with the ${\mathrm{TAN}}_{cl}$ and NoReFS was the best of them, with an accuracy close to 90%. According to the best model, patients whose age is above 35 years, have a severe vaginal infection, live in a rural area, use tobacco, have a family history of diabetes, and have had a personal history of hypertension are those with a high risk of developing preeclampsia.

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.

Introduction: Systematic reviews in education require methodological adaptations due to the complexity of educational data and contexts, making it necessary to adjust the PRISMA guidelines, initially designed for health, to meet the needs of the educational field. Objective: To adapt the PRISMA guidelines for their methodological implementation in systematic reviews within the educational domain. Methodos: A documentary and comparative analysis between PRISMA and educational studies was conducted, complemented by consultations with specialists, allowing the development of an adapted framework based on rigorous criteria and methodological tools tailored to education. Results: An adapted framework was proposed, including inclusion and exclusion criteria, methodological procedures, and tools for quality assessment, positively impacting the relevance, applicability, and rigor of educational systematic reviews. Conclusions: The adaptation of PRISMA to the educational field will enhance the quality of systematic reviews, strengthening their impact on policies, pedagogical strategies, and evidence-based teaching practices in complex contexts such as Latin America.

One of the most common causes of maternal deaths during pregnancy is preeclampsia. It is therefore important to analyze the resources needed to provide timely care and thus avoid health complications. One of those resources is hospital beds. Thus, to explore in-depth the inpatient beds occupation to treat preeclampsia at the IESS Los Ceibos Hospital in Guayaquil-Ecuador, Descriptive, Diagnostic, Predictive, and Prescriptive (DDPP) analytics will be applied together to the medical records collected retrospectively. In the descriptive analysis, the effects of the COVID-19 pandemic can be seen during the period March-September 2020. The diagnostic analysis helps us to show a consistent upward trend in the time series. In the predictive analysis, techniques such as Dynamic Bayesian Networks (DBN), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM), are considered to forecast the future inpatient beds occupation. The model trained with MLP achieved the lowest MAPE, which was 11.58%. It predicts that in September and November of 2024, there will be peaks of 274 and 258 inpatient beds, respectively. Finally, in our prescriptive analysis, we show that closing the hospitalization unit would produce, on average, 130.33 monthly referrals. To our knowledge, we do not find any work that applies all the DDPP analytics together in preeclampsia. Moreover, to our knowledge, there is no study that applies all the DDPP analytics together in univariate time series. Therefore, this work may serve as a basis for future studies in the joint application of all DDPP analytics to time series and to health.

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.