Hasna Chamlal

Feature selection is essential in machine learning and data science. Recently, there has been a growing effort to apply various mathematical methods to construct novel feature selection algorithms. In this study, we present a comprehensive state-of-the-art review of such techniques. We propose a new mathematical framework-based taxonomy to group the existing literature and provide an analysis of the research in each category from a mathematical perspective. The key frameworks discussed include variance-based methods, regularization methods, and Bayesian methods. By analyzing the strengths and limitations of each technique, we provide insights into their applicability across various domains. The review concludes with emerging trends and future research directions for mathematical methods in feature selection.

Background/Objectives: Corona virus disease 2019 (COVID-19) poses a threat to global public health. The early identification of critical cases is crucial to providing timely treatment to patients. Here, we investigated whether the neutrophil levels could predict COVID-19 complications. Methods: We performed a retrospective study of patients with COVID-19, admitted to the Cheikh Khalifa International University Hospital, Casablanca, Morocco. Laboratory test results collected upon admission and during hospitalization were analyzed based on clinical information. Results: Our study revealed that a rise in neutrophil “PNN” levels was associated with respiratory deterioration and intubation. They were positively correlated with the procalcitonin and C-reactive protein levels. Interestingly, PNN (polynuclear neutrophil) levels on day 5 proved to be a better predictor of intubation, acute respiratory distress syndrome (ARDS), and mortality than the initial PNN counts, C-reactive protein, or procalcitonin. Moreover, binary logistic regression with stratified PNN-day 5 data revealed that a PNN level on day 5 > 7.7 (109/L) was an independent risk factor for mortality and ARDS. Finally, the PNN levels on day 5 and proinflammatory cytokine IL-6 were positively correlated. Conclusions: Our data showed that neutrophilia proved to be an excellent predictor of complications and mortality during hospitalization and could be used to improve the management of patients with COVID-19.