- Email: email@example.com
- Thesis title: Predicting cancer outcomes from patient reported data and routine healthcare data
- Supervisors: Professor Anthony (Tony) G Cohn, FREng, CEng, CITP, Professor Vania Dimitrova, Professor Adam Glaser, Dr Amy Downing
I am a student in the UKRI Centre for Doctoral Training (CDT) in Artificial Intelligence for Medical Diagnosis and Care.
I graduated from Queen Mary University of London with an integrated Master’s degree in Biochemistry (MSci). Following graduation, I worked for a pharmaceutical company, Novartis, as a Medical Affairs Graduate. The main aim of my PhD project is to investigate whether AI techniques enable accurate prediction of cancer outcomes using Patient-Reported Outcome Measures (PROMs) and routinely collected health data to inform the production of robust personalised outcome prediction models. PROMs is a “report coming directly from patients about how they feel or function in relation to a health condition and its therapy without interpretation by healthcare professionals or anyone else” (Patrick et al, 2008). Cancer patients’ PROMs represent an important part of assessing patient quality of life, indicating whether the treatment has improved a patient’s symptoms, the type of experience of care patients have received at the practice, whether the patient’s health and well-being is improving. Cancer survival in the UK has doubled in the last 40 years; 50% survive cancer for 10 or more years (2010-11 data). However, UK survival rates are still below the rates in similar countries. Predicting long term outcomes following cancer treatment is crucial. These prediction models will address the quality of survival as well as absolute duration of survival.
My primary area of research is the prediction of cancer outcomes, such as survival and health care utilisation, using machine learning in the form of:
- Regression-based analyses may reveal informative relationships and patterns of healthcare utilisation
- Support vector machine, random forests for survival prediction
- Long short-term memory networks which allow feature exploration and multi-dimensional space prediction
- MSci in Biochemisitry, Queen Mary University of London, UK