Summary: This project developed new computer science technology for modelling the progression of a disease or developmental process. It pioneers the use of state-of-the-art generative modelling and learning techniques to address this problem.
Young, A.L. et al (2015). A simulation system for biomarker evolution in neurodegenerative disease, MedIA 26, pp 47-56.
Young, A.L. et al (2015). Multiple Orderings of Events in Disease Progression, LNCS 9123, pp 711-722. (IPMI 2015)
Young, A.L. et al (2014). A data-driven model of biomarker changes in sporadic Alzheimer’s disease, Brain 137, pp 2564-2577.
Oxtoby, N.P., et al (2014). Learning Imaging Biomarker Trajectories from Noisy Alzheimer’s Disease Data Using a Bayesian Multilevel Model, LNCS 8677, p 85. (Bayesian and grAphical Models for Biomedical Imaging, BAMBI 2014)
Huang, J. and Alexander, D. C. (2012). Probabilistic Event Cascades for Alzheimer’s disease, Advances in Neural Information Processing Systems 25, pp 3095-3103. (Neural Information Processing Symposium, NIPS 2012)
Fonteijn, H. et al (2012). An event-based model for disease progression and its application in familial Alzheimer’s disease and Huntington’s disease, NeuroImage 60(3), pp 1880–1889.
Fonteijn, H. et al (2011). An Event-Based Disease Progression model and its application to familial Alzheimer’s Disease, LNCS 6801, pp 748-759. (Information Processing in Medical Imaging, IPMI 2011)
NetMON: Network Models Of Neurodegeneration
Click to Open
Funding:
Biomarkers Across Neurodegenerative Diseases (BAND2): Alzheimer’s Association, Michael J. Fox Foundation for Parkinson’s Research, Alzheimer’s Research UK, Weston Brain Institute.
Summary: This project investigated the transneuronal hypothesis of disease propagation in Parkinson’s disease and Alzheimer’s disease. Our approach utilised modelling ideas from the NeuroProgression and EuroPOND projects.
Firth, et al. (2020), Sequences of cognitive decline in typical Alzheimer’s disease and posterior cortical atrophy estimated using a novel event-based model of disease progression, Alzheimer’s & Dementia.
Oxtoby, et al. (2017), Data Driven Sequence of Changes to Anatomical Brain Connectivity in Sporadic Alzheimer’s Disease, Frontiers in Neurology.
C-PLACID: Computational PLatform for Assessment of Cognition in Dementia
Summary: This project aims to develop new cognitive tests for early detection and accurate subtyping of dementia using traditional question and answer tests as well as new virtual reality scenario testing. The work draws on the ideas of disease progression modelling coming out of the NeuroProgression project.
Firth, et al. (2018). Longitudinal neuroanatomical and cognitive progression of posterior cortical atrophy, Brain 142, pp 2082–2095.
Firth, et al. (2020). Sequences of cognitive decline in typical Alzheimer’s disease and posterior cortical atrophy estimated using a novel event-based model of disease progression, Alzheimer’s & Dementia 16, pp 965-973.
Computational modelling of imaging markers in multiple sclerosis progression
Click to Open
Funding: MAGNIMS-ECTRIMS Fellowship and Multiple Sclerosis International Federation McDonald Fellowship.
Summary: Raz’s PhD project investigated the progression of neuroimaging measures in typical Alzheimer’s disease and Posterior Cortical Atrophy. The aim is to develop specialised mathematical models that allow us to compare the temporal heterogeneity of different Alzheimer’s disease variants.
Key publications:
Marinescu, R.V. et al. (2017). A Vertex Clustering Model for Disease Progression: Application to Cortical Thickness Images, IPMI 2017.
Marinescu, R.V. et al. (2019). DIVE: A spatiotemporal progression model of brain pathology in neurodegenerative disorders. NeuroImage 192, 166-177.
Summary: Alex’s postdoctoral fellowship extended the event-based model for accurate subtyping of dementia, with applications to screening and stratification for clinical trials.
Key publication:
Young, A.L. et al. (2018). Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference, Nature Communications 9, 4273.
Fine-grained staging and stratification in Huntington’s disease through computational models of disease progression
Summary: Pete’s postdoctoral work involved building disease progression models of Huntington’s disease using data from two large studies: Track-HD and Predict-HD.
Key publication:
Wijeratne, A.L. et al. (2018). An image-based model of brain volume biomarker changes in Huntington’s disease. Ann Clin Transl Neurol. 5, 570.
Designing user interfaces to support front-end clinical decision-making in neurodegenerative disease
Summary: Maura’s PhD project focussed on making POND models useful for clinicians, including visualisation and decision support.
Key publications:
Bellio, M et al. (2021). Opportunities and Barriers for Adoption of a Decision-Support Tool for Alzheimer’s Disease, ACM Trans. Comput. Healthcare 2.
Young, A.L. et al. (2014). A data-driven model of biomarker changes in sporadic Alzheimer’s disease, Brain 137, pp 2564-2577.
Heeks, R. (2006). Health information systems: Failure, success and improvisation, International Journal of Medical Informatics, 75(2), 125-137.
Blandford, A. et al. (2014). Patient safety and interactive medical devices: realigning work as imagined and work as done, Clinical risk, 20(5), 107-110.
Funding: NIHR UCL Hospital Biomedical Research Centre (Healthcare Engineering & Imaging Theme).
Dates: 2019 – 2021
Personnel: Gonzalo Castro Leal (RA), Timothy Whitfield, Jonathan Schott, Daniel Alexander, Zuzana Walker (Co-PI), Neil Oxtoby (PI).
Summary: Use POND modelling to analyse over 20 years of historical data (clinical and imaging) from the Essex Memory Clinic, in collaboration with Zuzana’s CODEC study. Key outputs include results on differential diagnosis of dementias and prognostic applications including a pilot prototype service for the memory clinic.
Computational models for clinical trial design in Huntington’s disease
Click to Open
Funding: UK Medical Research Council.
Dates: 2019-09 – 2022-08.
Personnel: Peter Wijeratne (Fellow).
Summary: Pete’s MRC Skills Development Fellowship aims to change the way disease modifying therapies in Huntington’s Disease are developed by designing early-phase clinical trials around computational models of disease progression. The project takes a two-step approach: first, redefine phenotypes using machine learning techniques applied to large multi-centre cohort data; second, use model-based analysis of multi-modal data — properly informed by the underlying biology — to reveal the disease mechanisms driving the observed phenotypes, and identify key biomarkers.
Learning personalised trajectories in Huntington’s disease through computational models of disease progression
Click to Open
Funding: CHDI Foundation.
Dates: 2020-03 – 2022-08
Personnel: Peter Wijeratne (PI), Daniel Alexander, Sarah Tabrizi (Huntington’s disease group).
Summary: This project advanced on our recent developments in computational modelling of Huntington’s disease (HD) to establish a staging system that can both stratify patients and estimate rate of progression and time between key pathological events. As a first-of-its-type, this system offered personalised disease trajectories using data-driven methods applied to clinical, imaging, and genotype data. Such patient-specific information can be used to provide fine-grained stratification for clinical trials, and potentially aid in treatment planning in a clinical setting.
PASSIAN: Piloting A Secure, Scaleable Infrastructure for AI in the NHS
Click to Open
Funding: MRC, Artificial intelligence for better biomedical and health research (
link).
Dates: 2022-09 – 2023-03
Personnel: Bojidar Rangelov (PDRA), Marcella Montagnese (PDRA, Cambridge), Tom Doel (Software Developer, Code Choreography), David Llewellyn (Co-I, Exeter), Zuzana Walker (Co-I), Timothy Rittman (Co-I, Cambridge), Neil Oxtoby (PI).
Summary: In this 6-month sprint project we built a cloud-based federated learning framework for enabling research on routinely collected data in two NHS memory clinics: Essex and Addenbrookes.
