Research Title: Association Between Modifiable Lifestyle Factors and Onset of Cardiovascular Disease
Why did you apply for this internship?
My major is mathematics and statistics. Since I’ve already gained a solid foundation in statistical theory, I’m eager to apply this knowledge to real-world applications. This internship is a great opportunity for me to obtain hands-on experience with real data. My motivation also comes from the belief that researching health-related issues is both meaningful and impactful. I would love to explore this field further.
What did you hope to gain in completing this project?
Through this project, I hoped to strengthen my data analysis skills by working with real-world datasets and applying statistical methods in a practical context. I also wanted to improve my communication skills and gain a deeper understanding of real health issues - how they are identified, analysed using data, and potentially addressed through evidence-based approaches.
Project Overview
The project explores the association between lifestyle factors and major adverse cardiovascular events (MACE) using UK Biobank data. The work involved extensive data cleaning, handling of missing values with multiple imputation, logistic regression modelling, variable selection and validation through bootstrap resampling.
What were the key results of your research project?
The model identified several lifestyle factors significantly associated with MACE and showed moderate predictive ability, with an AUC of about 0.71confirmed by bootstrap validation.
How do you feel you have benefited from completing this internship and has it made you consider future career paths?
It's an impactful experience of working with health-related data. This internship made me realise how complicated real-world data can be. It also showed me how much methodological choices matter, sometimes more than the result themselves. The more I look into them, the more I see there is still a lot to explore. Therefore, I decided to extend it to my undergraduate math project, and I will also apply for a master's program in health data science.