Institute of Biomedical Engineering (IBME),
Old Road Campus Research Building (ORCRB),
University of Oxford,
I am concurrently a GSK Postdoctoral Fellow in Digital Biomarkers, a Junior Research Fellow at St Cross College, University of Oxford, and a Postdoctoral Researcher at the Oxford Wearables Laboratory led by Prof. Aiden Doherty at the Big Data Institute (BDI), University of Oxford.
My Research Profiles:
My research aims to explore how we can capture digital biomarkers of disease using consumer digital health technologies (DHT)—collected from smartphone and smartwatch app. sensors and patient reported outcomes (PROs) when patients are at home—to develop personalised monitoring, enhance patient treatment strategies, and ultimately the development of validated digital biomarkers for clinical trial (CT) end-points and prescribed digital therapeutics (DTx). I have worked with CT data from patients in a range of Therapeutic Areas (TA) from multiple sclerosis to Parkinson’s disease, rheumatoid arthritis and dementia.
Clinical applications of AI/ML (machine learning) can act as powerful tools to learn complex and unseen digital patterns of disease, to help remotely monitor and identify signs of degeneration before they occur, and to understand new facets of habitual disease and disease phenotypes. My technical areas of expertise include AI/ML for disease prediction, explainable AI (XAI), and time-series analysis. I have a specific interest in creating interpretable, robust, and validated digital biomarkers through explainable AI (XAI) frameworks.
I obtained my DPhil. (PhD) in Clinical Machine Learning at the University of Oxford, developing digital biomarkers in collaboration with industrial partners, F. Hoffmann-La Roche.
Prior to my DPhil. I hold a bachelor’s degree (BAI, BA) in Biomedical Engineering and master’s degree (MAI) in Neural Engineering from Trinity College, the University of Dublin. My research at Trinity investigated the use of machine learning techniques to predict the onset of dementia in later life, through the characterisation of gait and cognitive performance from routine clinical assessments conducted during the Irish Longitudinal Study on Aging (TILDA).
medrXivDigital health technologies and machine learning augment patient reported outcomes to remotely characterise rheumatoid arthritismedrXiv 2022
IEEE OJEMBLongitudinal Trend Monitoring of Multiple Sclerosis Ambulation using SmartphonesIEEE Open Journal of Engineering in Medicine and Biology 2022
npj Sci. ReportsInterpretable deep learning for the remote characterisation of ambulation in multiple sclerosis using smartphonesNature Scientific Reports 2021
IEEE J-BHISmartphone- and Smartwatch-Based Remote Characterisation of Ambulation in Multiple Sclerosis During the Two-Minute Walk TestIEEE Journal of Biomedical Health Informatics 2021
Physiol. Meas.Smartphone-based remote assessment of upper extremity function for multiple sclerosis using the Draw a Shape TestPhysiological Measurement 2020
arXivSelf-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable DataarXiv preprint 2022