Population Data Science at Swansea University is excited to welcome this year’s cohort of Summer Interns. This summer, 16 talented interns have joined us as part of our team.
Over the next 4 days, we will highlight 4 interns daily in our blog posts, sharing insights into their projects and aspirations for the internship period.
We asked this year’s interns to tell us a little about their projects and what they hope to achieve by the end of the internship.
Anahita Zamanidehkordi
What were you studying before you started your internship?
Before starting this internship, I completed my MSc in Data Science at Swansea University.
What made you want to apply for an internship with Population Data Science?
I applied for this internship to gain hands-on experience applying data science methodologies to real-world challenges. I am eager to contribute to impactful projects that utilise large-scale data to improve public health and wellbeing.
Could you tell us a little about the project you are working on?
I am working on a project to improve data linkage techniques using packages such as Splink. This involves training models to predict match weights and analysing these predictions to develop more effective thresholds for identifying matches.
What skills do you hope to develop, and what outcomes are you aiming to achieve over the summer?
I will further develop my skills in data analysis, Python programming, and data integration. This internship will enhance my proficiency with industry standard tools, preparing me for future roles in data science and analytics.
Do you have a career in mind, and how do you hope the internship will help you towards that goal?
My career goal is to pursue a path in data science research, particularly in health informatics and population-level data analysis. This internship will provide invaluable experience in tackling complex data challenges and contributing to impactful research, aligning perfectly with my long-term career aspirations.
Line Manager: Mike Edwards. Mentor: James Kemmery.
Constantinos Constantinides
What were you studying before you started your internship?
I am a final-year PhD student in Population Neuroimaging at the University of Bath’s Department of Psychology.
What made you want to apply for an internship with Population Data Science?
In addition to gaining insight into the multidisciplinary field of population data science, the internship provides an opportunity to further develop my programming and data analysis skills as well as familiarise myself with commonly used administrative data sources within the SAIL Databank.
Could you tell us a little about the project you are working on?
The project aims to develop a reproducible and validated method for creating a population spine for residents of Wales, using the Welsh Demographic Service Dataset (WDSD) available within the SAIL Databank. This work involves comparing and identifying potential divergences in demographic profiles derived from WDSD with those generated by other sources, such as the Office for National Statistics (ONS), as part of the Administrative Data Research Wales Major Societal Challenges programme.
What skills do you hope to develop, and what outcomes are you aiming to achieve over the summer?
I am currently developing my SQL/R programming and data visualisation skills. Over the next few weeks, I expect to generate several tables and figures providing helpful insights for future directions and toward addressing the primary aims of the project.
Do you have a career in mind at the moment, and how do you hope the internship will help you towards that goal?
After completing my internship and PhD studies, I hope to take a health data science or epidemiology-related role within the healthcare sector or academia; the soft and technical skills that I am currently developing as part of the internship should help me get there.
Line Manager: Hoda Abbasizanjani. Mentor: Stuart Bedston.
Issie Hazell
What were you studying before you started your internship?
I have just finished my BSc in Population Health and Medical Science at Swansea University.
What made you want to apply for an internship with Population Data Science?
Throughout my degree, my interest in research grew, despite saying I absolutely did not want to go into research at the start of it! I undertook my own research evaluating options and potential benefits of screening and integrated treatment for comorbid attention deficit hyperactivity disorder (ADHD) and hypermobility disorders for my dissertation project, which solidified my interest in research. I applied for the internship to gain real-life research experience and improve and develop my skills to help me with further study and work.
Could you tell us a little about the project you are working on?
I am carrying out an overview of systematic reviews evaluating the efficacy of pain management services for persistent pain. My review is part of a bigger project that will use simulated data to understand how the services I have identified would impact the Welsh population if implemented.
What skills do you hope to develop, and what outcomes are you aiming to achieve over the summer?
I hope to develop my literature review skills, such as building search strategies, screening literature for relevance to the research question, and summarising evidence for various audiences. I am also looking forward to developing my statistical analysis skills using R. I will be writing a report on my literature review, which will be used to inform the wider project and communicate our findings to the Welsh Government.
Do you have a career in mind at the moment, and how do you hope the internship will help you towards that goal?
I am aiming for a career in some aspect of research, although I don’t know what yet! I’m hoping the internship will help me find the areas I am most interested in, and provide the skills for me to achieve that.
Line Manager: Athena Sheppard. Mentor: Rowena Bailey
Joseph McLaughlin
What were you studying before your internship?
I am studying Medicine at Swansea University. I am in my Third Year and if all goes well, this time next year, I will be a Junior Doctor.
What made you want to apply to Population Data Science?
I was initially interested because of the work I have seen using the SAIL Databank. I was fascinated by the idea of having access to NHS data on such a scale and the possible research outputs from such a resource. Last summer, I was a Population Data Science intern and found the experience incredibly valuable, which motivated me to apply again this year.
Could you tell us a little about the project you are working on?
I am working on a project that is looking into applying three publicly available magnetic resonance imaging (MRI) data processing pipelines to a few of the cohort studies from the Dementias UK Data Portal (DPUK). The aim is to compare the quality of the outputs from these pre-processing pipelines using a machine learning model and use the ability of the machine learning model to predict patient age based on this processed data to assess the quality of the pipeline’s processing of the data.
What skills do you hope to develop, and what outcomes are you aiming to achieve over the summer?
This summer I plan to develop my understanding of how data is pre-processed for AI and machine learning (ML) models and how this can influence the ability of models to correctly make predictions. I also hope to build on my skills as an ML model engineer. The output I will be working on is, firstly, the pre-processed datasets from each of the combinations of data pipelines and cohort studies. Creating these processed datasets is incredibly computationally expensive (time and energy). Pre-making these resources will help speed up other researchers’ analysis times. Secondly, I hope to compare these outputs by building a machine learning model that can predict the age of the subject of the MRI based on the output data from the pipelines and compare the quality of the pipelines based on the model’s predictions.
Do you have a career in mind at the moment and how do you hope the internship will help you towards that goal?
I am currently studying medicine and hope to become a Radiologist one day. My summer project will help me gain a foundation in the research side of neuroimaging, the steps used in processing data before training machine learning models, and the differences made in applying the same models to the same datasets, but using different processing steps. This knowledge, I believe, will be essential to effective medical practice in the age of AI and Machine Learning.
Line Manager: Emma Squires. Mentor: Lewis Hotchkiss.
For the latest updates on our Intern Programme, visit https://popdatasci.swan.ac.uk/about-us/summer-internship-programme/