As we reach the final part of our summer intern blog series, we’re introducing the last five members of this year’s cohort. Reflecting on their experiences so far, they tell us about their projects, the knowledge and skills they’re developing, and how the internship will benefit their future careers.
Rodgers Iradukunda
Where and what were you studying before you started your internship?
I am a third-year PhD student in Geographic Data Science at the University of Liverpool. My PhD focuses on improving the measurement of inequality within cities by considering its multidimensionality and its social, spatial, and cumulative implications.
What attracted you to apply to the Population Data Science internship programme?
I see it as a great opportunity to work on a real-world project that has the potential to improve people’s lives, while also boosting my future employability. It’s also a chance to sharpen my data science skills and learn something new.
Could you tell us a little about the project you will be/are working on?
The project I’m working on focuses on geographic inequalities in environmental and socioeconomic indicators across Wales. We’re ultimately interested in identifying vulnerable populations most at risk from environmental hazards such as flooding, heat stress, and air pollution.
What do you hope to learn, achieve, or contribute during your time with us?
I hope to learn more about the intersection of data science, epidemiology, and policy. It’s a rare opportunity to work in a space where multiple domains come together for a common good, especially as an intern. I’m also hoping to experience the city of Swansea, make new friends, and build my professional network.
Do you have a career in mind at the moment, and how do you hope the internship will help you towards that goal?
I’m hoping to work as a data science researcher. This internship will give me the skills needed for that role, as well as a glimpse into what the job actually involves.
Saad Kamran Kiyani
Where and what were you studying before you started your internship?
I completed my undergraduate degree in Computer Engineering at NUST in Pakistan. I’m now studying for my MSc in Data Science at Swansea University, doing this internship alongside the programme. Having studied engineering first gave me a system’s thinking approach; breaking problems into components and understanding how they fit together. That’s proving useful here.
What attracted you to apply to the Population Data Science internship programme?
I first heard about this internship programme through my lecturer at Swansea University. What attracted me was the chance to apply data science to real-world data and gain hands-on experience in data handling that goes beyond just academic projects.
Could you tell us a little about the project you will be/are working on?
I will be designing and building a modular pre-processing pipeline for tabular health data. It needs to handle numerical variables, categorical data, text, and time-series all in one system. The first part is analytical: I will be examining DPUK data to map out their structures, where data is missing, and what each dataset needs before it can be analysed. Once I understand the patterns, I will translate those into reusable pipeline components. Beyond that, I will implement validation checks that flag problems before they break downstream analysis, and create documentation along with data dictionaries so someone else can actually use these tools. Finally, I will test and present the pipeline’s outputs using real DPUK dementias datasets to demonstrate that it works reliably on genuine health data.
What do you hope to learn, achieve, or contribute during your time with us?
This is my first professional environment outside academia. Beyond the obvious, better collaboration, time management, and data science skills, what I really want is to understand what it means to build something that’s actually used. Not ‘this works on my laptop,’ but ‘this works when someone else runs it, breaks it, fixes it, and maintains it.’ That’s a different kind of thinking, and it’s the part I’m most keen to learn. In return, I hope to contribute by delivering a pipeline that genuinely meets that standard: well-built, well-documented, and reliable enough for the team to depend on.
Do you have a career in mind at the moment, and how do you hope the internship will help you towards that goal?
I’m planning to build a career in data science. My choice to do this internship is deliberate: I want to show employers I can work with genuine data under governance constraints, build things that are reproducible and maintainable, and contribute to systems that actually run-in production. That’s exactly what employers hiring for data science roles look for.
Sangeetha Subash Chandra Bose
Where and what were you studying before you started your internship?
I graduated from the University of Liverpool with an MSc in Health Data Science.
What attracted you to apply to the Population Data Science internship programme?
I applied for the internship because, during my MSc, I became really interested in population health research and how routinely collected healthcare data can be used to answer important clinical questions. I had learned the theory and analytical methods at University, but I wanted hands-on experience working with real-world data in a research environment. The opportunity to work with the SAIL Databank really stood out because it’s such a valuable resource for health research in the UK. I see it as a chance to apply my skills in R and SQL, learn how data are prepared and managed, and understand the practical side of research beyond the classroom.
Could you tell us a little about the project you will be/are working on?
I’ll be developing a PEDW Coverage Report to support Data Quality (DQ) checks in the SAIL Databank. The aim is to create a report that can be rerun after every data refresh to monitor whether the data continues to provide the expected level of coverage across various dimensions. As part of the project, I’ll help identify changes and shifts in coding patterns, as well as increases in missing data, that could affect research. I’ll also contribute to creating code lookups, making it easier to consistently classify activity and improve future data quality checks. Ultimately, the project will help ensure the PEDW data remains reliable and suitable for research and service evaluation.
What do you hope to learn, achieve, or contribute during your time with us?
During my internship, I hope to develop a strong understanding of how data quality is maintained for large healthcare data and how these checks support reliable research. I’m particularly interested in learning how coverage reporting complements existing data quality frameworks by identifying changes in coding, completeness, and consistency across data refreshes. I also hope to strengthen my technical skills by developing reusable scripts and producing clear visualisations to support ongoing monitoring. Knowing that my work can continue to support researchers beyond the internship is particularly rewarding.
Do you have a career in mind at the moment, and how do you hope the internship will help you towards that goal?
I would like to build a career in data analytics or data science, ideally within healthcare or public health, where I can use data to support research and improve decision-making. I’m especially interested in working with large datasets, understanding data quality, and developing analytical tools that help ensure research is based on accurate and reliable information. This internship provides an excellent opportunity to gain practical experience with real-world healthcare data, understand the processes involved in maintaining high-quality research data, and develop valuable technical and problem-solving skills, whilst also learning how data supports healthcare research and service evaluation. I believe this experience will give me a strong foundation for a future career in healthcare data analytics and help me apply my academic knowledge in a meaningful, real-world setting.
Shuyuan Zhang
Where and what were you studying before you started your internship?
I was studying Population Health Science (Data Science) at University College London.
What attracted you to apply to the Population Data Science internship programme?
I am drawn to this programme because it offers a rare opportunity to engage in data analysis and research that can inform policymaking and contribute to evidence-based policy decisions. It also allows me to work with experienced professionals, gaining more hands-on experience in real-world data analysis and research. I find this programme deeply meaningful and extremely valuable for both my personal growth and future contributions.
Could you tell us a little about the project you will be/are working on?
I will be working on a project about flood risk exposure, deprivation, and access-constrained communities in Wales. The project aims to understand how flooding affects different communities, especially those that may already face higher levels of deprivation or have limited access to services and transport routes. My work will involve using Welsh data to replicate and adapt previous research conducted in England. This may include combining flood risk, population, deprivation, and geographical data, conducting statistical analysis, and producing visualisations, such as maps. The aim is to help build evidence that can support better policy decisions and emergency planning in Wales.
What do you hope to learn, achieve, or contribute during your time with us?
During my time with the programme, I hope to gain more hands-on experience in real-world data analysis and research. I would like to better understand how population data can be used to identify social and environmental challenges, and how research evidence can support policymaking. I also hope to improve my technical skills, especially in data cleaning, statistical analysis, geospatial analysis, and data visualisation. More importantly, I hope my work can contribute to the people of Wales by helping identify communities that may be more vulnerable to flood risk, deprivation, or limited access to services. In the long term, I hope this can support better planning and help reduce inequalities.
Do you have a career in mind at the moment, and how do you hope the internship will help you towards that goal?
At the moment, I am interested in developing a career related to health data science. After this internship, I plan to return to university to study a master’s degree in Health Data Science, where I hope to build stronger skills in data science, statistics, and the use of data in health-related research. I hope this internship will help me understand how data analysis is applied in real-world research and policy contexts. It will also give me valuable hands-on experience before I start my postgraduate studies. In the future, I would like to work in a role where I can use health data, data science, and possibly AI-related methods to produce meaningful insights and contribute to better health outcomes and policy decisions.
Vikas Vyas
Where and what were you studying before you started your internship?
I completed MSc. Health Data Science from University College London in Sep 2025. I was working as a Consultant at ACESO Global Health Consultants till June 2026, working on NIHR-funded public health projects. I was working on producing data visualisations for the 3 ongoing projects. Additionally, I was working on Wellcome Mental Health Data prize bid to produce an interface through which researchers could access EHR or public health records for their research.
What attracted you to apply to the Population Data Science internship programme?
I saw the testimonies of the people who had interned during the Summer of 2025 at PDS, Swansea University and how valuable their time here was. The learning opportunity was incredible and the post-internship placement record looked great. This attracted me to research more about the positions and when the posting was made, I immediately applied to my current project, catering my experience towards the requirements of this role. I had already worked with linkage at UCL during my dissertation and was comfortable with tools like Python, R, and SQL, which are crucial for this role. The work I’ll be doing in Project 16 has very tangible real-world impact and this was the ultimate reason I decided to pursue this role here. Lastly, I was quite impressed with my Manager, Mike’s, portfolio in linkage and really wanted to learn more under him.
Could you tell us a little about the project you will be/are working on?
I’m working on Project 16 as a Data Science Intern. I am designing and building a GUI interface that will allow technical and non-technical users to build their own cohorts and customise parameters for in-depth evaluation. The SAIL databank datasets – used for building these cohorts – will be linked via advanced linkage algorithms built on the Splink library and advanced statistical analysis will be possible with the results. This project will allow users to upload their own datasets, or link with SAIL databank and import EHR data, play around with settings and parameters, and give them full control over the results in an automatic pdf report generated. Later, the project also aims to build an LLM trained on linkage and being able to build the cohorts for the users just by talking to it.
What do you hope to learn, achieve, or contribute during your time with us?
I have already learnt a lot about linkage theory, record matching, and deduplication of datasets using advanced algorithms. My main learning has come from building synthetic datasets in Python, designing the GUI interface in Figma, and implementing the application to be run using Streamlit. I will also be looking into building a solid understanding of C# for the front and back end of the application development. Even though my background is not in software development, this project will provide me with a very good knowledge of real-world data science application development. Such opportunities are unheard of for short-term internship projects. I hope to build this application so that users can streamline their healthcare research and build their cohorts without wasting time. This application will have massive impact on the linkage field and will improve user experience within the SAIL databank using SeRP.
Do you have a career in mind at the moment, and how do you hope the internship will help you towards that goal?
I want to continue working in research, specifically, building applications or working on AI and data science projects that improve the field of healthcare. My passion lies in healthcare research, and I believe this internship is the best thing for advancing my career. I am developing real skills during this internship in Python, SQL, Git, C# – all the tools that will help me maximise my impact wherever I work next. I am very grateful for this opportunity!
For the latest updates on our Intern Programme, visit https://popdatasci.swan.ac.uk/about-us/summer-internship-programme/