Elliot Wadge

Radiotherapy plays a role in 40% of all cancer cures making it an important tool in modern cancer treatment. However, patient heterogeneity with respect to radiosensitivity greatly impacts the effectiveness of radiotherapy treatment causing large unwanted variation in patient outcomes. This means that some patients may receive too little or an excessive dose depending on their intrinsic radiosensitivity. This project aims to address the existing challenges in personalized cancer treatment by combining machine learning and human genomics, specifically focusing on intrinsic radiosensitivity in head-and-neck and colorectal cancer. The complexity of genetic pathways makes it difficult to untangle what is important and unimportant within the genes, but machine learning offers a way to identify these relationships and correlations. A large amount of genomic information for cancer patients is available which may be correlated with their radiotherapy treatment outcomes. This information will be used in the training of machine learning algorithms which will then predict patient radiosensitivity. If successful this could help inform patient-specific treatment planning paving the way for more effective and tailored cancer treatments.