The Hong Kong Polytechnic University Featured PhD Programmes
University of Dundee Featured PhD Programmes
University College London Featured PhD Programmes
University of Oxford Featured PhD Programmes
The Hong Kong Polytechnic University Featured PhD Programmes

(MRC DTP) "And Now, Today’s Pain Forecast" - Putting Predictive Models in Patients’ Pockets

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  • Full or part time
    Dr J McBeth
    Prof W Dixon
    Prof D Schultz
    Dr T House
  • Application Deadline
    No more applications being accepted
  • Competition Funded PhD Project (European/UK Students Only)
    Competition Funded PhD Project (European/UK Students Only)

Project Description

A third of the UK population has chronic pain. Pain severity and the impact it has on patient’s lives varies from day to day, it has a major impact on patient-perceived control and is one of the main reasons for poor quality of life. Producing individualised pain forecasts for forthcoming days would provide a degree of control and improve patient’s lives.
The new era of consumer healthcare using patient’s own technology opens many opportunities, but also provides new challenges. Analysing patterns within temporally-rich pain data, and identifying causal relationships with similarly granular exposure data is too complex for existing ‘off-the-shelf’ algorithms.
This project will develop smartphone-delivered clinically meaningful pain forecasts for people living with chronic pain.
The work will use the uniquely rich dataset from Cloudy with a Chance of Pain, a UK-based smartphone study where 13,000 people with chronic pain reported daily pain severity and other factors affecting their pain (e.g., sleep, mood, physical activity). Daily symptoms were co-located with weather from the nearest station. This PhD project will develop bespoke analysis methods using cutting-edge mathematical and computational expertise to predict levels of pain severity. Crucially, the developed models will be capable of extension, both in terms of including additional variables as more is learned about chronic pain, and to other diseases.
Individual’s pain trajectories will be estimated using two approaches. The first is based on model-averaged GP-SSM, with the second using time-asymmetric conjugate statistical learning. Subgroup discovery will be conducted by evaluating distances between distributions and clustering methods.
The impact of the work will come via three routes:
1. Development of pain forecasts that are implementable within a smartphone app, incorporating methods to present uncertainty. This will benefit people living with chronic pain by allowing them to plan future activities around this knowledge.
2. Development of methodology for i) within-person trajectories using daily ordinal data and ii) discovering clusters of individuals who have different responses to exposure variables (here, weather).
3. An enhanced understanding of the day-to-day patterns of symptoms in patients with chronic pain, and triggers of pain flares.

Centre for Epidemiology:
David Schultz:

Entry Requirements:
Applications are invited from UK/EU nationals only. Applicants must have obtained, or be about to obtain, at least an upper second class honours degree (or equivalent) in a relevant subject.

Funding Notes

This project is to be funded under the MRC Doctoral Training Partnership. If you are interested in this project, please make direct contact with the Principal Supervisor to arrange to discuss the project further as soon as possible. You MUST also submit an online application form - full details on how to apply can be found on the MRC DTP website

As an equal opportunities institution we welcome applicants from all sections of the community regardless of gender, ethnicity, disability, sexual orientation and transgender status. All appointments are made on merit.


Frigola, F. Lindsten, T. B. Schön, and C. E. Rasmussen. Bayesian inference and learning in Gaussian process state-space models with particle MCMC. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 26 (2013) 3156–3164.
S. Särkkä, A. Solin, and J. Hartikainen. Spatiotemporal learning via infinite-dimensional Bayesian filtering and smoothing. IEEE Signal Processing Magazine, 30(4):51–61, 2013.
T. House, R. Vahid Roudsari and L. Dawson, Beta distribution-valued process learning of longitudinally assessed clinical performance in dental education. Submitted.
B. J. Frey and D. Dueck, Clustering by Passing Messages Between Data Points. Science 315, 972–976, 2007.
J. A. Peachey et al., How forecasts expressing uncertainty are perceived by UK students, Weather 68(7) (2013): 176–181.
N. Bansback, M. Harrison, and C. Marra, Does introducing imprecision around probabilities for benefit and harm influence the way people value treatments?, Medical Decision Making 36(4) (2015): 490–502.

FindAPhD. Copyright 2005-2019
All rights reserved.