Andrew P. Creagh

Postdoctoral Research Associate @ University of Oxford | GSK Postdoctoral Fellow
D.Phil. in Clinical Machine Learning from the University of Oxford.

Institute of Biomedical Engineering (IBME),

Old Road Campus Research Building (ORCRB),

University of Oxford,

OX37DQ, UK.


Welcome

I am a Postdoctoral Researcher at the Computational Health Informatics (CHI) laboratory at the University of Oxford led by Prof. David A. Clifton.

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 Wearables Laboratory led by Prof. Aiden Doherty at the Big Data Institute (BDI), University of Oxford.

My Departmental Website
My College Website

Research

My research aims to explore how we can capture digital biomarkers of disease, through continuously collecting smartphone and smartwatch measurements when patients are at-home. I work mainly with patients who have neurdegenerative and autoimmune diseases, such as multiple sclerosis, rheumatoid arthritis, Parkinson’s disease and dementia.

Clinical applications of machine learning (ML) 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. I have a specific interest in creating interpretable, robust, and transparent models through explainable AI (XAI) frameworks.

Background

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).

news

Jun 18, 2022 Our new preprint: “Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data” is now available on arXiv 📢.
Feb 24, 2022 Our new preprint: “Longitudinal Trend Monitoring of Multiple Sclerosis Ambulation using Smartphones” is now available on medrXiv 📢.
Nov 1, 2021 Announced as this year's recipient of the prestigious IET William James Award 🥳.
Jul 15, 2021 Our new explainable AI (XAI) paper is now available online in Nature Scientific Reports 🥳.
Jun 16, 2021 Awarded Junior Research Fellowship (JRF) St Cross College, University of Oxford.
Apr 12, 2021 Awarded STEM for Britain Medal at the UK Houses of Parliament

selected publications

  1. medrXiv
    Longitudinal Trend Monitoring of Multiple Sclerosis Ambulation using Smartphones
    Creagh, A. P., Dondelinger, F., Lipsmeier, F., Lindemann, M., and De Vos, M.
    medrXiv 2022
  2. Sci. Reports
    Interpretable deep learning for the remote characterisation of ambulation in multiple sclerosis using smartphones
    Creagh, A. P., Lipsmeier, F., Lindemann, M., and De Vos, M.
    2021
  3. IEEE J-BHI
    Smartphone- and Smartwatch-Based Remote Characterisation of Ambulation in Multiple Sclerosis During the Two-Minute Walk Test
    Creagh, A. P., Simillion, C., Bourke, A. K., Scotland, A., Lipsmeier, F., Bernasconi, C., Beek, J., Baker, M., Gossens, C., Lindemann, M., and De Vos, M.
    2021
  4. Physiol. Meas.
    Smartphone-based remote assessment of upper extremity function for multiple sclerosis using the Draw a Shape Test
    Creagh, A. P., Simillion, C., Scotland, A., Lipsmeier, F., Bernasconi, C., Belachew, S., Beek, J., Baker, M., Gossens, C., Lindemann, M., and De Vos, M.
    2020
  5. arXiv
    Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data
    Yuan, H, Chan, S., Creagh, A. P., Tong, C., Clifton, D. A., and Doherty, A.
    arXiv preprint 2022