I have developed my career in biomedical research, building on my expertise in machine learning, computing and mathematics, but specialising in intrapartum (in labour) fetal monitoring. I am now leading an ambitious programme to develop data-driven decision-support software in this clinical field. I am uniquely positioned to achieve this by working with the world’s largest and most complete birth cohort of routine labour data (100,000 deliveries).
At the same time, I am leading an ambitious multidisciplinary international project, as one of the 13 performers in the Wellcome LEAP In-Utero programme. My team is working to develop novel, potentially game-changing technology for continuous fetal monitoring, allowing us to go well beyond fetal heart rate and identify babies at risk of still birth early on.
I obtained a BSc(Hons) in Applied Mathematics from the Technical University of Sofia (Bulgaria) and a PhD in Computer Science from Portsmouth University. I joined the Nuffield Department of Obstetrics and Gynaecology and the Institute of Biomedical Engineering at Oxford for a post-doctoral position in 2007. In 2016 I was awarded a NIHR Career Development Fellowship to grow my independent research group. In the same year, I became a Research Fellow at Wolfson College and also joined the newly formed Big Data Institute at Oxford.
At Wolfson College, I lead the Cross-disciplinary Machine Learning Cluster which brings together researchers across different disciplines to share and learn about the impact of machine learning in their respective fields.
AWARDS AND GRANTS
2022-2025 Performer in the In-Utero Wellcome LEAP programme
2022-2023 Invention for Innovation National Institute for Health Research (NIHR) FAST Award (£49,983)
2021-2024 Invention for Innovation National Institute for Health Research (NIHR) Product Development Award (£1,118,105)
2021-2024 EPSRC Healthcare Technologies with Dr Ivan Jordanov (£600,069)
2021-2025 Collaborator on the Norwegian Research Council's funded, Oslo-based HOME-study: Home monitoring of pregnancies at risk, led by Annetine Staff and Aase Pay (approx. £1.3M)
2017-2021 NIHR Career Development Fellowship (£559,468)
2020-2021 The University Challenge Seed Fund (£56,450)
2020-2021 Medical and Life Sciences Translational Fund (£68,300)
2012-2016 Action Medical Research (£133,262)
BSc (Hons) PhD
Associate Professor, Group Lead - Oxford Labour Monitoring
- Wolfson College Research Fellow, where I lead the Cross-disciplinary Machine Learning (XML) cluster
- Based jointly at the Big Data Institute and the Nuffield Department of Women's and Reproductive Health
Committed to preventing fetal compromise in labour
I am leading a research team to develop and integrate in the clinical setting a novel data-driven cardiotocography (CTG) systems/software to continuously assess fetal wellbeing at the onset of and during term labour. CTG is the gold standard worldwide to detect if a fetus may benefit from an emergency delivery. Unreliable, empirical CTG interpretation will be replaced with quantified computer- and data-based individualised risk assessment.
We already have a prototype system (OxSys), as the starting point. It is derived from a large birth cohort (100,000 term deliveries) by systematic analysis of computer-based CTG features and clinical risk factors in relation to perinatal outcomes. In tests 'off-line' with the data, the current prototype has shown to perform better than clinicians in clinical practice. We have developed a tablet app that runs OxSys in real time data at the John Radcliffe Hospital, analysing all CTGs as they are being taken (maternity admission unit, delivery suite or wards). We are continuously improving the app's interface in collaboration with the clinicians. The app takes in information from the user about any risk factors if present and modifies the analysis accordingly.
In the coming years, we will continue to use 'big data' to derive new understanding and improved methods for CTG interpretation in the patient-specific clinical context. Beyond this, we will ensure refined optimal performance of OxSys on the birth cohort; validate OxSys on additional data from Oxford & London (approx. 40,000 births). We will then take the first steps towards translation to the bedside.
Our work will potentially benefit families, clinicians and healthcare systems by reducing brain injuries, perinatal deaths and unnecessary interventions
International Workshop on Signal Processing and Monitoring in Labour 2017 - Computerized data-driven interpretation of the intrapartum CTG: progress at Oxford
International Workshop on Signal Processing and Monitoring in Labour 2019 - Big data for intrapartum fetal monitoring: OxSys developments
Dlugatch R. et al, (2024), BMC Med Ethics, 25
Multimodal Deep Learning for Predicting Adverse Birth Outcomes Based on Early Labour Data
Asfaw D. et al, (2023)
Tolladay J. et al, (2023), Bioengineering, 10, 775 - 775
Dlugatch R. et al, (2023), BMC Medical Ethics, 24
Lear CA. et al, (2023), BJOG: An International Journal of Obstetrics & Gynaecology