Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.
  • Intake: OxKEN

PROJECT OVERVIEW

This project will use routinely collected clinical data from electronic medical records across Europe to develop machine learning algorithms for the identification of subjects at high risk of developing psoriatic arthritis amongst those with a diagnosis of psoriasis.

The data have all been previously mapped to a common data model (as used in the EHDEN project - www.ehden.eu) and so can be combined for federated analysis. Large databases of primary care electronic medical records including >20 million UK subjects (CPRD GOLD and AURUM) will be used to develop machine learning algorithms.  Embedded within the large epidemiology group led by Dani, you will be taught how to apply different machine learning methods including Regularized logistic regression, Random forests, Gradient boosting machines, Decision trees, Naive Bayes, K-nearest neighbours, Neural networks and Deep learning (Convolutional neural networks, Recurrent neural network and Deep nets) methods.

The best performing algorithms will be made available to the community in an interactive web environment (see here for an example of prediction algorithms for the identification of subjects with rheumatoid arthritis at risk of infections, cardiovascular disease, and cancer).

This work will feed into a large European consortium aiming to predict the development of PsA and will inform future projects including development of an interventional study aiming to prevent PsA in people with psoriasis. This work will particularly inform the identification of patients at increased risk for PsA by clarifying the optimal inclusion and exclusion criteria to define an at-risk population for the future interventional trial.

 KEYWORDS

Disease inception, psoriasis, machine learning, epidemiology, psoriatic arthritis

TRAINING OPPORTUNITIES

Biostatistics, big data, epidemiology, machine learning, specialist psoriatic arthritis and combined rheum/derm clinics, presentations at national and international meetings, link into large European PsA consortium investigating predictors of PsA development.

KEY PUBLICATIONS

  1. Coates Laura C, Moverley Anna R, McParland Lucy, Brown Sarah, Navarro-Coy Nuria, O’Dwyer John L, Meads David M, Emery Paul, Conaghan Philip G, Helliwell Philip S. (2015) Effect of tight control of inflammation in early psoriatic arthritis (TICOPA): a UK multicentre, open-label, randomised controlled trial. Lancet; 386(10012):2489-98.
  2. van Mens Leonieke JJ, van de Sande Marleen GH, van Kuijk Arno WR, Baeten Dominique, Coates Laura C. (2018) Ideal target for psoriatic arthritis? Comparison of remission and low disease activity states in a real-life cohort. Ann Rheum Dis;77(2):251-257.
  3. Lane JCE, Weaver J, Kostka K, Duarte-Salles T, Abrahao MTF, Alghoul H, Alser O, Alshammari TM, Biedermann P, Banda JM, Burn E, Casajust P, Conover MM, Culhane AC, Davydov A, DuVall SL, Dymshyts D, Fernandez-Bertolin S, Fišter K, Hardin J, Hester L, Hripcsak G, Kaas-Hansen BS, Kent S, Khosla S, Kolovos S, Lambert CG, van der Lei J, Lynch KE, Makadia R, Margulis AV, Matheny ME, Mehta P, Morales DR, Morgan-Stewart H, Mosseveld M, Newby D, Nyberg F, Ostropolets A, Park RW, Prats-Uribe A, Rao GA, Reich C, Reps J, Rijnbeek P, Sathappan SMK, Schuemie M, Seager S, Sena AG, Shoaibi A, Spotnitz M, Suchard MA, Torre CO, Vizcaya D, Wen H, de Wilde M, Xie J, You SC, Zhang L, Zhuk O, Ryan P, Prieto-Alhambra D; OHDSI-COVID-19 consortium. Risk of hydroxychloroquine alone and in combination with azithromycin in the treatment of rheumatoid arthritis: a multinational, retrospective study. Lancet Rheumatol. 2020 Nov;2(11):e698-e711. doi: 10.1016/S2665-9913(20)30276-9.
  4. Roca-Ayats N, Balcells S, Garcia-Giralt N, Falcó-Mascaró M, Martínez-Gil N, Abril JF, Urreizti R, Dopazo J, Quesada-Gómez JM, Nogués X, Mellibovsky L, Prieto-Alhambra D, Dunford JE, Javaid MK, Russell RG, Grinberg D, Díez-Pérez A. GGPS1 Mutation and Atypical Femoral Fractures with Bisphosphonates. N Engl J Med. 2017 May 4;376(18):1794-1795.
  5. Bayliss LE, Culliford D, Monk AP, Glyn-Jones S, Prieto-Alhambra D, Judge A, Cooper C, Carr AJ, Arden NK, Beard DJ, Price AJ. The effect of patient age at intervention on risk of implant revision after total replacement of the hip or knee: a population-based cohort study. Lancet. 2017 Apr 8;389(10077):1424-1430. doi: 10.1016/S0140-6736(17)30059-4.

CONTACT INFORMATION OF ALL SUPERVISORS

Laura Coates

Daniel Prieto-Alhambra

Sara Khalid