Jorge Daniel Mello-Román

The global COVID-19 pandemic has generated extensive datasets, providing opportunities to apply machine learning for diagnostic purposes. This study evaluates the performance of five supervised learning models—Random Forests (RFs), Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Logistic Regression (LR), and Decision Trees (DTs)—on a hospital-based dataset from the Concepción Department in Paraguay. To address missing data, four imputation methods (Predictive Mean Matching via MICE, RF-based imputation, K-Nearest Neighbor, and XGBoost-based imputation) were tested. Model performance was compared using metrics such as accuracy, AUC, F1-score, and MCC across five levels of missingness. Overall, RF consistently achieved high accuracy and AUC at the highest missingness level, underscoring its robustness. In contrast, SVM often exhibited a trade-off between specificity and sensitivity. ANN and DT showed moderate resilience, yet were more prone to performance shifts under certain imputation approaches. These findings highlight RF’s adaptability to different imputation strategies, as well as the importance of selecting methods that minimize sensitivity–specificity trade-offs. By comparing multiple imputation techniques and supervised models, this study provides practical insights for handling missing medical data in resource-constrained settings and underscores the value of robust ensemble methods for reliable COVID-19 diagnostics.

Academic performance plays a key role in assessing the quality and equity of a country’s educational system. Studying the aspects or factors that influence university academic performance is an important research opportunity. This article synthesizes research that employs machine learning techniques to identify the determinants of academic performance in first-year university students. A total of 8700 records from the Complutense University of Madrid corresponding to all incoming students in the academic year 2022–2023 have been analyzed, for which information was available on 28 variables related to university access, academic performance corresponding to the first year, and socioeconomic characteristics. The methodology included feature selection using Random Forest and Extreme Gradient Boosting (XGBoost) to identify the main predictors of academic performance and avoid overfitting in the models, followed by analysis with four different machine learning techniques: Linear Regression, Support Vector Regression, Random Forest, and XGBoost. The models showed similar predictive performance, also highlighting the coincidence in the predictors of academic performance both at the end of the first semester and at the end of the first academic year. Our analysis detects the influence of variables that had not appeared in the literature before, the admission option and the number of enrolled credits. This study contributes to understanding the factors that impact academic performance, providing key information for implementing educational policies aimed at achieving excellence in university education. This includes, for example, peer tutoring and mentoring where high- and low-performing students could participate.

University dropout rates are a problem that presents many negative consequences. It is an academic issue and carries an unfavorable economic impact. In recent years, significant efforts have been devoted to the early detection of students likely to drop out. This paper uses data corresponding to dropout candidates after their first year in the third largest face-to-face university in Europe, with the goal of predicting likely dropout either at the beginning of the course of study or at the end of the first semester. In this prediction, we considered the five major program areas. Different techniques have been used: first, a Feature Selection Process in order to identify the variables more correlated with dropout; then, some Machine Learning Models (Support Vector Machines, Decision Trees and Artificial Neural Networks) as well as a Logistic Regression. The results show that dropout detection does not work only with enrollment variables, but it improves after the first semester results. Academic performance is always a relevant variable, but there are others, such as the level of preference that the student had over the course that he or she was finally able to study. The success of the techniques depends on the program areas. Machine Learning obtains the best results, but a simple Logistic Regression model can be used as a reasonable baseline.

Skin dermoscopy images frequently lack contrast caused by varying light conditions. Indeed, often low contrast is seen in dermoscopy images of melanoma, causing the lesion to blend in with the surrounding skin. In addition, the low contrast prevents certain details from being seen in the image. Therefore, it is necessary to design an approach that can enhance the contrast and details of dermoscopic images. In this work, we propose a multi-scale morphological approach to reduce the impacts of lack of contrast and to enhance the quality of the images. By top-hat reconstruction, the local bright and dark features are extracted from the image. The local bright features are added and the dark features are subtracted from the image. In this way, images with higher contrast and detail are obtained. The proposed approach was applied to a database of 236 color images of benign and malignant melanocytic lesions. The results show that the multi-scale morphological approach by reconstruction is a competitive algorithm since it achieved a very satisfactory level of contrast enhancement and detail enhancement in dermoscopy images.

Panoramic dental radiography is one of the most used images of the different dental specialties. This radiography provides information about the anatomical structures of the teeth. The correct evaluation of these radiographs is associated with a good quality of the image obtained. In this study, 598 patients were consecutively selected to undergo dental panoramic radiography at the Department of Radiology of the Faculty of Dentistry, Universidad Nacional de Asunción. Contrast enhancement techniques are used to enhance the visual quality of panoramic dental radiographs. Specifically, this article presents a new algorithm for contrast, detail and edge enhancement of panoramic dental radiographs. The proposed algorithm is called Multi-Scale Top-Hat transform powered by Geodesic Reconstruction for panoramic dental radiography enhancement (MSTHGR). This algorithm is based on multi-scale mathematical morphology techniques. The proposal extracts multiple features of brightness and darkness, through the reconstruction of the marker (obtained by the Top-Hat transformation by reconstruction) starting from the mask (obtained by the classic Top-Hat transformation). The maximum characteristics of brightness and darkness are added to the dental panoramic radiography. In this way, the contrast, details and edges of the panoramic radiographs of teeth are improved. For the tests, MSTHGR was compared with the following algorithms: Geodesic Reconstruction Multiscale Morphology Contrast Enhancement (GRMMCE), Histogram Equalization (HE), Brightness Preserving Bi-Histogram Equalization (BBHE), Dual Sub-Image Histogram Equalization (DSIHE), Minimum Mean Brightness Error Bi-Histogram Equalization (MMBEBHE), Quadri-Histogram Equalization with Limited Contrast (QHELC), Contrast-Limited Adaptive Histogram Equalization (CLAHE) and Gamma Correction (GC). Experimentally, the numerical results show that the MSTHGR obtained the best results with respect to the Contrast Improvement Ratio (CIR), Entropy (E) and Spatial Frequency (SF) metrics. This indicates that the algorithm performs better local enhancements on panoramic radiographs, improving their details and edges.

Kernel partial least squares regression (KPLS) is a non-linear method for predicting one or more dependent variables from a set of predictors, which transforms the original datasets into a feature space where it is possible to generate a linear model and extract orthogonal factors also called components. A difficulty in implementing KPLS regression is determining the number of components and the kernel function parameters that maximize its performance. In this work, a method is proposed to improve the predictive ability of the KPLS regression by means of memetic algorithms. A metaheuristic tuning procedure is carried out to select the number of components and the kernel function parameters that maximize the cumulative predictive squared correlation coefficient, an overall indicator of the predictive ability of KPLS. The proposed methodology led to estimate optimal parameters of the KPLS regression for the improvement of its predictive ability.

Kernel partial least squares regression (KPLS) is a technique used in several scientific areas because of its high predictive ability. This paper proposes a methodology to simultaneously estimate both the parameters of the kernel function and the number of components of the KPLS regression to maximize its predictive ability. A metaheuristic optimization problem was proposed taking the cumulative cross-validation coefficient as an objective function to be maximized. It was solved using nature-inspired metaheuristic algorithms: the genetic algorithm, particle swarm optimization, grey wolf optimization and the firefly algorithm. To validate the results and have a reference measure of the efficiency of the nature-inspired metaheuristic algorithms, derivative-free optimization algorithms were also applied: Hooke-Jeeves and Nelder-Mead. The metaheuristic algorithms estimated optimal values of both of the kernel function parameters and the number of components in the KPLS regression.