Support vector machines (SVMs) are well-known machine learning algorithms for classification and regression applications. In the healthcare domain, they have been used for a variety of tasks including diagnosis, prognosis, and prediction of disease outcomes. This review is an extensive survey on the current state-of-the-art of SVMs developed and applied in the medical field over the years. Many variants of SVM-based approaches have been developed to enhance their generalisation capabilities. We illustrate the most interesting SVM-based models that have been developed and applied in healthcare to improve performance metrics on benchmark datasets, including hybrid classification methods that combine, for instance, optimization algorithms with SVMs. We even report interesting results found in medical applications related to real-world data. Several issues around SVMs, such as selection of hyperparameters and learning from data of questionable quality, are discussed as well. The several variants developed and introduced over the years could be useful in designing new methods to improve performance in critical fields such as healthcare, where accuracy, specificity, and other metrics are crucial. Finally, current research trends and future directions are underlined.

In machine learning, hyperparameter tuning is strongly useful to improve model performance. In our research, we concentrate our attention on classifying imbalanced data by cost-sensitive support vector machines. We propose a multi-objective approach that optimizes model’s hyper-parameters. The approach is devised for imbalanced data. Three SVM model’s performance measures are optimized. We present the algorithm in a basic version based on genetic algorithms, and as an improved version based on genetic algorithms combined with decision trees. We tested the basic and the improved approach on benchmark datasets either as serial and parallel version. The improved version strongly reduces the computational time needed for finding optimized hyper-parameters. The results empirically show that suitable evaluation measures should be used in assessing the classification performance of classification models with imbalanced data.

In this paper, we propose optimization models to address flexible staff scheduling problems and some main issues arising from efficient workforce management during the Covid-19 pandemic. The adoption of precautionary measures to prevent the pandemic from spreading has raised the need to rethink quickly and effectively the way in which the workforce is scheduled, to ensure that all the activities are conducted in a safe and responsible manner. The emphasis is on novel optimization models that take into account demand requirements, employees’ personal and family responsibilities, and anti-Covid-19 measures at the same time. It is precisely considering the anti-Covid-19 measures that the models allow to define the working mode to be assigned to the employees: working remotely or on-site. The last optimization model, which can be viewed as the most general and the most flexible formulation, has been developed to capture the specificity of a real case study of an Italian University. In order to improve employees’ satisfaction and ensure the best work/life balance possible, an alternative partition of a workday into shifts to the usual two shifts, morning and afternoon, is proposed. The model has been tested on real data provided by the Department of Mechanical, Energy and Management Engineering, University of Calabria, Italy. The computational experiments show good performance and underline the potentiality of the model to handle worker safety requirements and practicalities and to ensure work activities continuity. In addition, the non-cyclic workforce policy, based on the proposed workday organization, is preferred by employees, since it allows them to better meet their needs.

In this paper, we study two well‐known problems that are attracting increasing attention in the last years: patient admission and patient‐to‐room assignment problems. These two problems are often complicated by some patients, which may have fluctuations in length of stay (LOS). We propose an optimization model that plans patient admissions and patient stays considering fluctuations in LOS and does not allow overcrowded rooms, as typically required in real‐world cases. We develop an efficient matheuristic approach based on large neighborhood search and fix and optimize heuristic. We tested our optimization model and some variations of the objective function on benchmark instances from the literature. The computational results indicate the effectiveness of the proposed methods in improving the quality of care offered to the patients. Furthermore, the proposed approach can provide a useful support to decision makers for patient flow management and avoid disruptions in access to care due to bed shortages.