Undergraduate, master and MRes students
In collaboration with Imperial College London, we have students joining us for semester to work on a research project. We also welcome international students when we can.
Since 2016, we have welcomed and worked with 20+ students. Some students took an interest in purely AI and mathematics whereas others undertook a hybrid project involving clinical care and research.
If you have an idea that could fit within our research, please do get in touch! We would love to hear your thoughts and how we could work together.
I worked within the Computational Oncology Lab group for my first MRes project rotation. My project was on the cost of common primary brain tumours and their economic burden on the English healthcare system.
At first, as with being the new member in any scenario, I felt intimidated. I had just graduated with my undergraduate in Biomedical Sciences the previous summer. With little programming language knowledge and minimal experience from my undergraduate dissertation, I knew I had to work twice as hard to understand how to approach data. Moreover, I did not know anything about health economics or how the NHS operated. I took the time to learn Python and SQL and balanced that with formulating a methodology to assign costs to over 50,000 patients and tens of thousands of rows of data. While my project aims and expected results were thoroughly discussed before my analysis began, I still had the independence and freedom to approach data the way I wanted to. I was not creatively limited in my research; I had the opportunity to look at things I found interesting within data that was still relevant to my project and the general population of brain tumour patients.
Although I felt out of place the first few weeks of joining the laboratory, my supervisors, Dr Matthew Williams and Kerlann Le Calvez would meet with me regularly and would take the time to explain everything to me. They provided a safe environment where I could discuss any issues I had. From choosing ICD-10 diagnosis codes to writing SQL queries, they would always promptly answer and provide thorough explanations to make sure I understood why I was taking specific approaches. I highly appreciated that my supervisors took the time to clarify my understanding of the data rather than just telling me what to do. This has helped me tremendously when writing my thesis and preparing for my viva, giving me confidence when discussing data.
I also had the opportunity to join productive lab meetings with other lab members within the group. I felt a sense of participation, integration, and inclusion among the lab community. Learning about the different research going on within the group made me appreciate the amount of work that goes into research and boosted my scientific creativity. Being surrounded by dedicated scientists and clinicians who have strong beliefs and passions for healthcare and the importance of using big data to understand care and outcomes inspired me further when conducting research for my project.
Ultimately, I learned more in these few months than I anticipated. I improved my Python and SQL abilities and feel more confident approaching large datasets. I also learned a lot more about health economics than I knew, an area I did not think I would enjoy as much as I did. Lastly, under the utmost supervision and guidance, I contributed to research that makes a considerable economic argument for improving care for brain tumour patients.
WORK PUBLISHED BY THE STUDENTS
ASSESSING K-NEAREST NEIGHBOURS ALGORITHM FOR SIMPLE, INTERPRETABLE TIME-TO-EVENT SURVIVAL PREDICTIONS OVER A RANGE OF SIMULATED DATASETS
August 05, 2019
P. Kroupa, C. Morton, K. Le Calvez, M. Williams