Biography
Stelios is a PhD student in the Cardiovascular Epidemiology Unit, supervised by Professor Angela Wood. He is funded by the HDR UK Big Data for Complex Disease Driver Programme, and his PhD investigates developing dynamic risk prediction models to target concomitant diseases and their interactions. Stelios completed his MEng in Computer Science at Durham University. His dissertation investigated estimating acute medical patients' short-term risk of deterioration using interpretable machine learning. Prior to beginning his PhD, Stelios gained industry experience through roles in data science R&D at Evergreen Life, and software engineering at Deutsche Bank. Additionally, his research on predicting Accident & Emergency (A&E) admissions and readmissions using explainable machine learning has been recognised and endorsed by the National Institute for Health Research (NIHR) and formed part of a Department of Health and Social Care policy briefing on addressing winter pressures in the NHS and also won the best talk award at the Society for Acute Medicine International Conference 2023.
Research
Health Data Science, AI in Healthcare, Dynamic Survival Analysis, AI Fairness and Ethics, Deep Generative Modelling
Publications
Watson, M., Boulitsakis Logothetis, S., Green, D., Holland, M., Chambers, P., & Al Moubayed, N. (2024). Performance of machine learning versus the national early warning score for predicting patient deterioration risk: a single-site study of emergency admissions. BMJ Health & Care Informatics, 31(1), Article e101088. https://doi.org/10.1136/bmjhci-2024-101088
Boulitsakis Logothetis, S., Green, D., Holland, M. et al. Predicting acute clinical deterioration with interpretable machine learning to support emergency care decision making. Sci Rep 13, 13563 (2023). https://doi.org/10.1038/s41598-023-40661-0
Boulitsakis Logothetis, S. Fairness-Aware Naïve Bayes Classifier for Data with Multiple Sensitive Features. Proc. AAAI 2022 Spring Symposium on Achieving Wellbeing in AI, Stanford University, Palo Alto, California, USA, Mar. 21- 23, 2022. https://ceur-ws.org/Vol-3276/SSS-22_FinalPaper_69.pdf
