BSL-HEE

Hireves is an interactive tool that combines human expertise and AI-driven optimization to improve the allocation of emergency medical vehicles. It enhances decision-making by integrating qualitative and quantitative data, reducing response times, and maximizing coverage.

This project leverages Bayesian methods with INLA and Stan to analyze survival data, modeling latent variables with the Zero-Modified Power Series distribution. Applications focus on lung cancer and melanoma to enhance survival predictions and treatment evaluations.

This project leverages time series analysis and machine learning techniques to predict sales for a jewelry company, aiming to enhance forecasting accuracy and optimize inventory management

This project employs Bayesian Compositional Data time series models in INLA to analyze and predict market shares, providing insights for strategic decision-making

This project develops Bayesian mixed models and robust methods to evaluate agreement metrics between medical devices, focusing on outlier accommodation and clinical applications in COPD diagnostics. It includes software development to enhance accessibility for researchers and clinicians.

This project applies Bayesian Dirichlet models to investigate the effects of stress on vaginal microbiome composition in a Spanish cohort, providing insights into how stress-related changes in microbiota can impact health

Statistical Machine Learning in Environmental Health leverages algorithms to understand the impacts of environmental factors like air pollution on public health outcomes, particularly during the COVID-19 pandemic.