DrEvangelos Chandakas

I am an Honorary Research Fellow in Computational Epidemiology within the Department of Medicine, School of Public Health at Imperial College London (ICL). My research primarily focuses on applying statistical and AI methods in environmental epidemiology, computational epidemiology, exposure science and medical informatics. I actively contribute to numerous projects exploring the impact of environmental stressors on human health. Additionally, I am involved in designing and developing microsimulation-based tools for modeling and forecasting the dynamic risks associated with non-communicable diseases (NCDs). These tools facilitate informed decision-making and enable the implementation of effective strategies to combat NCDs. Furthermore, I have dedicated significant attention to comparing feature selection techniques using machine learning in high-performance computing infrastructures to identify important features for predictive models.

My research interests span several areas, including AI in medical science, computational epidemiology, bioinformatics, analytical chemistry, simulations, computational biology, metabolomics, wide association studies, data analysis and management, platform design, and the application of advanced computational and simulation schemes in pharmacokinetic, toxicokinetic, and environmental models.

My expertise also lies in conducting statistical, medical, and interpretive analyses of Real-World Data (RWD), which encompasses electronic health records (including oncology records), claims, registries, and medical ontologies. Additionally, I provide, develop, and implement innovative solutions to address Real World Evidence (RWE) requirements.
I am also an active member of the Observational Health Data Sciences and Informatics (OHDSI) community, where I work extensively with Observational Medical Outcomes Partnership (OMOP) data for various health studies. My involvement includes developing ETL (Extract, Transform, Load) data pipelines as well as analyze health data. This work ensures the high quality and reliability of data, facilitating robust and reproducible research in health sciences.

I tackle complex business and research problems by leveraging advanced statistical and AI methods, such as generative AI, deep learning, mixed-effect modeling on longitudinal health data, trajectory-based modeling, cluster analysis, propensity score methods in pharmacoepidemiology, time series analyses, and Bayesian approaches.