Skip to main content

Machine learning for decision making: how to choose the optimal strategy for stratified medicine life cycle

Stratified medicine is at the cutting edge of a new era in healthcare, which targets to a specific patient population on the basis of a companion diagnostic (such as a biomarker) to predict treatment efficacy or adverse side effects.

The economic concern is the greatest hurdle for the broader life sciences community, in particular for the pharmaceutical industry, to embrace stratified medicine. Stratification strategies (cut-off score of the companion diagnostic) and drug-diagnostic development strategies can have a great impact on the profitability for product developers and manufacturers and also the medical treatment price for payers.

With the aim of addressing the economic knowledge gap in the stratified medicine life cycle (from clinical R&D, product manufacturing to commercialisation), this work will develop a decision tool coupled with integrated computational models to estimate expenditures and revenues during the stratified medicine life cycle.

This decision tool will combine with machine learning methods (e.g. decision tree, ANN, SVM...) to identify the key economic factors and to select the optimal strategies from an economic perspective. This work will help developers and manufacturers to avoid capital risk and to maximise profit.

Essential requirement: good at mathematics, coding experience (in Python or Matlab)

How to apply

If you are interested in applying for the above PhD topic please follow the steps below:

  1. Contact the supervisor by email or phone to discuss your interest and find out if you woold be suitable. Supervisor details can be found on this topic page. The supervisor will guide you in developing the topic-specific research proposal, which will form part of your application.
  2. Click on the 'Apply here' button on this page and you will be taken to the relevant PhD course page, where you can apply using an online application.
  3. Complete the online application indicating your selected supervisor and include the research proposal for the topic you have selected.

Good luck!

This is a self funded topic

Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: The UK Government is also offering Doctoral Student Loans for eligible students, and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.

Meet the Supervisor(s)

Yang Yang - Dr. Yang is a Lecturer in Chemical Engineering.  She has multidisciplinary background of BSc and MSc in Computer Science and PhD in Chemical Engineering.   Dr. Yang has twelve-years academic experience of applying her data science and machine learning knowledge for multi-field process modelling and analysis. In 2011, Dr. Yang received her PhD degree sponsored by Overseas Research Scholarships (ORS) and Tetley & Lupton Scholarships (TLS) from University of Leeds. During her PhD, she successfully applied data mining and machine learning techniques to identify the optimal composition of nano-photocatalyst (TiO2). Besides five high quality journal papers, the decisional tool designed and developed by Dr. Yang, which combined with Process analytical technology (PAT) and machine learning techniques, was sponsored and adopted by GlaxoSmithKline Pharmaceuticals (GSK) for its nanoparticle product line.    Dr. Yang joined Imperial College London and then University College London as a postdoctoral research associate. During this period, Dr. Yang accumulated great knowledge and experience in biopharmaceutical manufacturing process and personalised medicine and established collaborations with both academical and industrial partners. Collaborated with UCB and Eli Lily, the leaders of biopharmaceutical industries in UK, Dr. Yang established process models and Cost of Goods (CoGs) models of biomanufacturing process with discrete-event modelling and Monte Carlo simulation manufacturing facility fit analysis. A decision-support tool which combined the process models, CoGs models and machine learning models using decision tree algorithms had been greatly complimented by biopharmaceutical industry users. Supported by world leading pharmaceutical companies, Pall Corporation, Merck and Medimmune, Dr. Yang’s independent research of digital twins for continuous biomanufacturing process was awarded £5000 funding by Future targeted healthcare manufacturing hub in UCL. Dr. Yang has led a collaboration with Shanghai Pulmonary Hospital (China) to construct a decision-support tool with big data analysis for personalized diagnosis and treatment of lung cancer.