Home

UCL’s Progression Of Neurodegenerative Disease (POND) Initiative is developing new computational models and techniques for learning characteristic patterns of disease progression using large cross-sectional data sets. Our focus is currently on dementias, such as Alzheimer’s disease, but our techniques have wider application to other diseases and developmental processes.

We are considering a broad approach to modelling disease progression, starting with the work of Hubert Fonteijn (NeuroImage 2012) on event-based models, and also exploring the possibility of determining causal links between events. Events constitute biomarker abnormality, which includes image-based biomarkers such as regional atrophy in the brain, as well as biomarkers such as levels of abnormal proteins in cerebrospinal fluid.

All the while, we ensure clinical relevance in the models through collaboration with the Dementia Research Centre at UCL’s Institute of Neurology.

UCL POND started with an EPSRC-funded project (see here for more details) and are coordinators of the subsequent EuroPOND consortium (a Horizon 2020 project).

Featured publications (see our publications page for all of our publications):

  • Imaging plus X: multimodal models of neurodegenerative disease progression
    Neil Oxtoby, Danny Alexander, for the EuroPOND Consortium
    Current Opinion in Neurology 30, 371–379 (2017)
  • A simulation system for biomarker evolution in neurodegenerative disease
    A Young, N Oxtoby, S Ourselin, J Schott, D Alexander
    MedIA vol 26, p 47 (2015)
  • Modelling Non-Stationary and Non-Separable Spatio-Temporal Changes in Neurodegeneration via Gaussian Process Convolution
    M Lorenzi, G Ziegler, D Alexander, S Ourselin
    MLMMI 2015, LNCS vol 9487 (2015)
  • Multiple Orderings of Events in Disease Progression
    A Young, N Oxtoby, J Huang, R Marinescu, P Daga, D Cash, N Fox, S Ourselin, J Schott, D Alexander
    IPMI2015, LNCS vol 9123, p 711 (2015)
  • Efficient Gaussian Process-Based Modelling and Prediction of Image Time Series
    M Lorenzi, G Ziegler, D Alexander, S Ourselin
    IPMI2015, LNCS vol 9123, p 626 (2015)
  • A data-driven model of biomarker changes in sporadic Alzheimer’s disease
    A Young, N Oxtoby, P Daga, D Cash, N Fox, S Ourselin, J Schott, D Alexander
    Brain vol 137, p 2564 (2014)
  • Learning Imaging Biomarker Trajectories from Noisy Alzheimer’s Disease Data Using a Bayesian Multilevel Model
    N Oxtoby, A Young, N Fox, ADNI, P Daga, D Cash, S Ourselin, J Schott, D Alexander
    LNCS vol 8677, p 85 (2014)
  • Data-driven models of neurodegenerative disease
    A Young, N Oxtoby, J Schott, D Alexander
    ACNR vol 14, issue 5 (2014)
  • Predicting outcomes in clinically isolated syndrome using machine learning
    V Wottschel, D Alexander, P Kwok, D Chard, M Stromillo, N. De Stefano, A Thompson, D Miller, O Ciccarelli
    NeuroImage: Clinical, vol 7 p 281 (2014)
  • Prediction of Second Neurological Attack in Patients with Clinically Isolated Syndrome Using Support Vector Machines
    V Wottschel, O Ciccarelli, D Chard, D Miller, D Alexander
    Proceedings of PRNI 2013, p 82 (2013)
  • An event-based model for disease progression and its application in familial Alzheimer’s disease and Huntington’s disease
    H Fonteijn, M Modat, M Clarkson, J Barnes, M Lehmann, N Hobbs, R Scahill, S Tabrizi, S Ourselin, N Fox, D Alexander
    NeuroImage vol 60, p 1880 (2012)
  • An Event-Based Disease Progression Model and Its Application to Familial Alzheimer’s Disease
    H Fonteijn, M Clarkson, M Modat, J Barnes, M Lehmann, S Ourselin, N Fox, D Alexander
    LNCS vol 6801, p 748 (2011)
  • Probabilistic Event Cascades for Alzheimer’s Disease
    J Huang, D Alexander
    In Advances in Neural Information Processing Systems (NIPS), Lake Tahoe, CA, USA, December 2012