Data Analytics Research and Technology in Healthcare
(DARTH group)
Faculty
Athanasios Tsanas ('Thanasis') FAcadMathSci FRSE FRSM
Chair (Full Professor) in Digital Health and Data Science
Thanasis studied Biomedical Engineering, and completed a DPhil (PhD) in Applied Mathematics at the University of Oxford (2012). He joined the Usher Institute, University of Edinburgh in 2017 as a Chancellor’s Fellow, a prestigious 5-year tenure-track post. He secured tenure 2+ years early, and was promoted to a Personal Chair (Full Professor) in Digital Health and Data Science in 2022.
He has been consistently ranked amongst the world’s top scientists since 2020 according to the Stanford/Elsevier annual ranking list, particularly in the areas of Biomedical Engineering and AI. ScholarGPS named him “Top Scholar" for 2024, and currently rank him globally in the top 0.1% for lifetime impact in Machine Learning. His portfolio includes >£50m in grant income, with outputs of his work used in the NHS and explored by industrial partners including Intel, LSVT Global, GSK, Abbott, Roche, and others. He is Co-founder of the NHS Digital Academy, the world’s first national digital health informatics leadership programme (funded by NHS England), where he led the development and delivery of the 'Clinical Decision Support and Actionable Data Analytics' theme (2018-2022). Internationally, he served as a Scientific Advisor to the Ministry of Health, Greece.
He is a Founding Fellow of the Academy for the Mathematical Sciences (UK National Academy of Mathematics), a Fellow of the Royal Society of Edinburgh (Scotland's National Academy of Sciences), and a Fellow of the Royal Society of Medicine.
Post-doctoral researchers
Daniil Lisik
Research Fellow
Daniil studied Medicine at the University of Gothenburg, where he subsequently completed his PhD in 2025. His doctoral thesis focused on computational phenotyping of asthma and allergies, using machine learning and population-based epidemiological data to identify new subtypes of these conditions and investigate their risk factors and long-term health outcomes.
His postdoctoral research at Umeå University / Region Norrbotten builds on these research areas, with particular focus on longitudinal phenotyping of COPD, asthma, and respiratory symptoms. Beyond machine learning, his work involves causal inference, evidence synthesis, and meta-research on the topic of reporting guidelines and the use of large language models in systematic reviews and data exploration.
Daniil received a prestigious EU European Respiratory Society (ERS) Fellowship, and is conducting a phenotyping project at the DARTH group.
Victoria Ashley Lang
Research Fellow
Victoria studied Applied Mathematics at the University of California San Diego and Advanced Mathematics and Mathematical Engineering at the Universitat Politècnica de Catalunya, where she wrote her master’s thesis on numerical modelling of neuronal electrophysiology. Her doctoral research in Medical Science at the University of Gothenburg, funded in part by a Marie Skłodowska-Curie Actions (MSCA) doctoral fellowship, investigated the neural encoding of touch using statistical modelling and machine learning on human microneurography data. Previously, she worked on phantom limb pain, leading experimental studies on limb temperature in amputees and on body ownership. Earlier research roles took her into the neurobiology of feeding behaviour, underwater acoustic signal processing, and cardiovascular endocrinology.
Victoria joins the DARTH group as a research fellow on the AMBIENT-BD project, analysing sleep and circadian rhythm data to elucidate their relationship with clinical outcomes in bipolar disorder.
PhD students
Lauren Thomas
PhD student
Lauren studied Computer Science (Artificial Intelligence) at the University of Sheffield as an integrated Masters degree. During her final year she worked as a Research Assistant in the machine learning group on a project using machine learning to track Bumblebees. Her Masters research project was on improving accuracy of Prostate cancer diagnosis algorithms with continuous and federated learning.
Her PhD focuses on generating clinically actionable insights into endometriosis symptom trajectories on longitudinal self-reports, biological samples and information from digital technologies. She is supervised by Thanasis Tsanas, Andrew Horne and Philippa Saunders and is funded through the Precision Medicine DTP.
Dónal Heelan
PhD student
Dónal studied Computer Science, Linguistics and French at Trinity College Dublin, then went on to work as a Software Engineer at Unity Technologies. He subsequently completed a MSc in AI for Medicine and Medical Research at University College Dublin, where he interned at UCD’s GOLD Lab. His MSc thesis focused on evaluating machine learning algorithms' ability at identifying drivers of non-small cell lung cancer.
His PhD topic centres on “Clinically actionable insights into endometriosis symptom trajectories using longitudinal self-reports, biological samples and data from digital technologies”. The supervisory team is Thanasis Tsanas, Andrew Horne and Philippa Saunders and his funding is through the UKRI AI CDT in Biomedical Innovation.