Dr Evangelia Kyrimi

Profile

Dr Kyrimi is a lecturer in AI and Data Science in the School of Electronic Engineering and Computer Science at QMUL. Since 2023 she is a Royal Academy of Engineering Research Fellow. Dr Kyrimi is a statistician, specialised on medical statistics. She has attained her PhD in computer science at QMUL. Her thesis is titled “Bayesian Networks for Clinical Decision Making: Support, Assurance, Trust”. 

Dr Kyrimi's research interests lie in Bayesian modelling and decision support under uncertainty in healthcare. She focuses on methodologies for eliciting expert knowledge and developing causal graphical models. Her research is also about translating causal AI models into explainable and responsible AI systems that users can trust and adopt. This includes (1) investigating the fundamentals of explanation, (2) developing explanation algorithms that incorporate causality, (3) creating user-specific dynamic explanation outputs, and (4) generating an XAI evaluation protocol. She is also interested in understanding and bridging the existing gap between developing accurate clinical decision support systems and implementing them into practice. 

Research

Research Interests:

Research interests: 

• Explainable AI
• Responsible and trustworthy AI
• Causality
• Bayesian networks
• Counterfactual reasoning
• Expert elicitation
• Clinical decision support systems

Current research projects:

• ExAIDSS project “Explainable AI to ensure trust in clinical Decision Support Systems”, as part of my research fellowship provided by the Royal Academy of Engineering (collaborators: UCL Division of Psychology and Language Sciences, Living With company, Centre for Trauma Sciences, Agena)
• “Deploying Explainable AI to Reduce Time to Treatment in Trauma”, in collaboration with the Centre for Trauma Sciences

Previous research projects: 

• COMBAT-AID (COMputer Battlefield Assistance in Trauma care and injury Decision-support) project with the Centre for Trauma Sciences
• PamBayesian (PamBayesianPatient Managed Decision-Support using Bayesian Networks) was a 3-year EPSRC funded project to develop decision-support for chronic conditions.

Publications

Selected publications (For a full list of publications please visit my google scholar page ):

• Kyrimi, E., Stoner, R., Perkins, Z., Pisirir, E., JWohlgemut, J., Marsh, W., Tai, N. (2024). Updating and recalibrating causal probabilistic models on a new target population. Journal of Biomedical Informatics,149, DOI: 10.1016/j.jbi.2023.104572.
  
• Pisirir, E., Wohlgemut, J., Kyrimi, E. et al. (2023). A Process for Evaluating Explanations for Transparent and Trustworthy AI Prediction Models. IEEE 11th International Conference on Healthcare Informatics (ICHI), Houston, TX, USA, pp. 388-397, DOI: 10.1109/ICHI57859.2023.00058.
• Vasey, B., Nagendran, M., Campbell, B., Clifton, D.A., Collins, G.S., Denaxas, S., Denniston, A.K., Faes, L., Geerts, B., Ibrahim, M., Liu, X., Mateen, B.A., Mathur, P., McCradden, M.D., Morgan, L., Ordish, J., Rogers, C., Saria, S., Ting, D.S.W., Watkinson, P., Weber, W., Wheatstone, P., McCulloch, P. & DECIDEAI Expert Group. (2022). Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artifcial intelligence: DECIDE-AI. Nature Medicine 28, 924–933. DOI: 10.1038/s41591-022-01772-9 
• Wohlgemut, JM., Kyrimi, E., Stoner, RS., Pisirir, E., Marsh, W., Perkins, Z. & Tai, N. (2021). The outcome of a prediction algorithm should be a true patient state rather than an available surrogate. Journal of Vascular Surgery. DOI: 10.1016/j.jvs.2021.10.059 
• Kyrimi, E., McLachlan, S., Dube, K., Neves, M.R., Fahmi, A. & Fenton, N. (2021). A comprehensive scoping review of bayesian networks in healthcare: Past, present and future. Artificial Intelligence in Medicine, 117, 102108. DOI: 10.1016/j.artmed.2021.102108
• Kyrimi, E., Dube, K., Fenton, N, Fahmi, A., Neves, M., Marsh, W. & McLachlan, S. (2021). Bayesian Networks in Healthcare: What is preventing their adoption? Artificial Intelligence in Medicine. vol. 116, p. 102079. DOI: 10.1016/j.artmed.2021.102079
• Kyrimi, E., Neves, M., McLachlan, S., Neil, M., Marsh, W., & Fenton, N. (2020). Medical Idioms: Reasoning patterns to develop medical Bayesian Networks. Journal of Biomedical Informatics, DOI: 10.1016/j.jbi.2020.103495
• Kyrimi, E., Mossadegh, S., Tai, N., & Marsh, W. (2020). An incremental explanation of inference in Bayesian networks for increasing model trustworthiness and supporting clinical decision making. Artificial Intelligence in Medicine, 103. DOI: 10.1016/j.artmed.2020.101812
• McLachlan, S., Kyrimi, E., Dube, K., Hitman, G.A., Simmonds, J., & Fenton, N.E. (2020). Towards Standardisation of clinical care process specifications. SAGE Health Informatics Journal (HIJ). DOI: 10.1177/1460458220906069
• McLachlan, S., Dube, K., Hitman, G.A., Fenton, N.E., & Kyrimi, E. (2020). Bayesian Networks in Healthcare: Distribution by Medical Condition. Artificial Intelligence in Medicine (AIIM), 107. DOI: 10.1016/j.artmed.2020.101912
• Fahmi, A., MacBrayne, A., Kyrimi, E., McLachlan, S., Humby, F., & Marsh, W. (2020). Causal Bayesian networks for medical diagnosis: A case study in Rheumatoid Arthritis. Proceedings of the IEEE International Conference on Health Informatics (ICHI 2020). DOI: 10.1109/ICHI48887.2020.93743207

Grants

• Rosetrees Trust Interdisciplinary Award 2021, under theme - To Stimulate Collaborative Research between Medicine and Engineering.
• A 5 – year research fellowship from the Royal Academy of Engineering (2023 – 2028)