Completed Intern Projects

All projects completed through the NHS England Data Science PhD Internship Scheme, grouped by cohort wave.

Wave 11 - April to July 2026

• P116

  Applied Privacy Enhancing Technologies in Healthcare

  tbu

  Applying privacy-enhancing technologies including differential privacy to real-world NHS healthcare data.

  PETs Differential Privacy Tabular

• P115

  Genomic Data Incorporated into Healthcare Predictions

  Paula Gardner  ·  Supervised by Scarlett Kynoch

  Investigating the integration of genomic data into machine learning models for healthcare outcome prediction.

  PETs Differential Privacy Tabular

• P114

  Automatic Speech Recognition with Summarisation Evaluation

  Ziyuan Cai  ·  Supervised by Ben Wallace

  Evaluating automatic speech recognition systems with automated summarisation quality metrics for NHS healthcare settings.

  Synthetic Digital Twin Tabular

Wave 10 - February to April 2026

• P102

  Genomic Data Incorporated into Healthcare Predictions

  Auguste Rumbutyte  ·  Supervised by Scarlett Kynoch

  Investigating the integration of genomic data into machine learning models for healthcare outcome prediction.

  MachineLearning Precision Medicine Genomic Data

• P101

  Automatic Speech Recognition with Summarisation Evaluation

  Wing Leung  ·  Supervised by Ben Wallace

  Evaluating automatic speech recognition systems with automated summarisation quality metrics for NHS healthcare settings.

  Explainability ASR Audio

Wave 9 - July to December 2025

• P92

  Causal Inference to Estimate the Impact of Interventions

  Jamie Wong

  Exploring causal inference methods for estimating the impact of community health interventions from observational data.

  MachineLearning Causal Inference Tabular

  Code Report

• P91

  Automated Evaluation and Benchmarking of Data Linkage Quality

  Joseph Lam

  Automated metrics and benchmarking pipeline for evaluating data linkage quality and communicating transparency to end users.

  Linkage Evaluation Tabular

Wave 8 - January to June 2025

• P82

  EvalSense

  Adam Dejl  ·  Supervised by Jonny Pearson

  Comprehensive guidance and tooling for evaluating large language models (LLMs)

  Evaluation Text Data LLMs

  Code Report

• P81

  MM-HealthFair

  Konstantin Georgiev  ·  Supervised by Jonathan Hope | Jonny Pearson

  An end-to-end pipeline for multimodal fusion, evaluation and fairness investigation

  Fariness MultiModal Data Explainability

  Code Report

Wave 7 - June to December 2024

• P73

  VQA with GOSH

  Anjali Golding  ·  Supervised by Dan Schofield | Jonathan Hope

  Investigating the hurdles of applying VQA in a real-world healthcare setting

  Visual Question Answering Image Data MultiModal

• P72

  NER Evalaution with GOSH

  Avish Vijayaraghavan  ·  Supervised by Dan Schofield | Jonathan Hope

  Resource Constrained Annotation Workflow for Paediatric Histopathology Reports Using LLMs

  Histopathology Reports Text Data Annotations

  Code Report

• P71

  Privacy Leakage Extended

  Jenny Chim  ·  Supervised by Dan Schofield | Jonny Pearson

  Identifying Metrics, Mitigations and Models which can identify Leakage of sensitive content from Language Models

  Privacy Aware Models Text Data Indirect Leakage

  Code Report

Wave 6 - January to June 2024

• P62

  NHS Monitor Corpus

  Samuel Hollands  ·  Supervised by Dan Schofield

  Scraping and curation of NHS website data to create a corpus of representive text data

  Graph-based Web Scraping Text Data Corpus

  Code Report

• P61

  Understanding Fairness and Explainability in Multimodal Approaches within Healthcare

  Sophie Martin  ·  Supervised by Jonny Pearson

  Pipeline to compare the impact on fairness of using a fusion model versus a single modality model

  Fairness MultiModal Python

  Code Report

Wave 5 - June to November 2023

• P53

  Transforming Healthcare Data with Graph-based Techniques using SAIL DataBank

  Chris Tomlinson  ·  Supervised by Dan Schofield

  This project explored topological and semantic graph embeddings of relevant healthcare ontologies to enhance performance on downstream tasks.

  Representations of data Embeddings Python

• P52

  Exploring Process Mining with East Midlands Ambulance Service

  Alex Coles  ·  Supervised by Paul Carroll and Martina Fonseca

  In collaboration with East Midlands Ambulance Service, this work explored using Process Mining techniques to better understand the processes within the service.

  Process Mining Ambulances Python - PM4Py

  Code Report

• P51

  Investigating Privacy Concerns and Mitigations for Language Models in Healthcare

  Vicky Smith  ·  Supervised by Dan Schofield

  An initial exploration of privacy risks in healthcare language models, including privacy-preserving techniques applied before or after model training, and evaluating their effectiveness with privacy attacks.

  NLP Foundation Models Python

  Code Report

Wave 4 - January to May 2023

• P43

  Enriching Neurology Patient Information using MedCAT

  Aizaan Anwar  ·  Supervised by Paul Carroll and Jonny Pearson

  In collaboration with Lancaster Teaching Hospitals NHS Foundation Trust and Lancaster University, this work explored how to evaluate the embedding space generated for automated clinical coding tasks in Neurology.

  NLP Neurology Python - MedCAT

  Code Report

• P42

  Including Mortality in Hypergraphs for Multi-morbidity

  Zoe Hancox  ·  Supervised by Dan Schofield

  Building on previous hypergraphs work (P34) that can extract the impact of predecessor and successor diseases on disease progression pathways, this work looked to include an implicit relationship to demographics and consider the impact of mortality.

  Representations of Data Hypergraphs Python - Numba

  Code Report

• P41

  NHS Synth

  Harrison Wilde  ·  Supervised by Jonny Pearson

  This project focused on building a package for generating useful synthetic data, audited and assessed along the dimensions of utility, privacy and fairness. It gives the ability to experiment with different model architectures to find which are the most promising for real-world usage.

  Synthetic Data VAE Python

  Code Report

Wave 3 - June to December 2022

• P34

  Using Hypergraphs to Investigate the Impact of Comorbidities

  Jamie Burke  ·  Supervised by Dan Schofield & Kevin Fasusi

  In collaboration with Swansea University and the SAIL Databank, this work focused on the generation of hypergraphs for investigating the individual and joint impact of comorbidities on a patient pathway.

  Representations of Data Hypergraphs Python - Numba

  Code Report

• P33

  Exploring Large-scale Language Models with NHS Incident Data

  Niall Taylor  ·  Supervised by Dan Schofield

  In collaboration with the NHS England patient safety data team, an investigation into how to produce a useful and valid representation space when training a language model for a healthcare task.

  NLP DeCLUTR Python - Transformers

  Code Report

• P32

  Diabetes

  Stephen Richer  ·  Supervised by Paul Carroll

  In collaboration with East Suffolk and North Essex foundation trust to apply a suite of data science techniques to a large population health data including both primary and secondary care data.

  RAP Code PHM Data Python - OSNnx

  Code Report

• P31

  Txt-Ray Align Continued

  Sarah Hickman

  This project sought to identify the clinical application, pipeline and validation metrics for this work.

  Multi-modal Validation in Healthcare Python

  Code Report

Wave 2 - January to May 2022

• P24

  Using LIME to explain facial disease classification

  Anwesha Mohanty  ·  Supervised by Jonny Pearson

  Application of Local Interoperable Model-agnostic Explanations to an InceptionV3 classifier looking at a Rosacea

  Model Explainability LIME Python

  Code Report

• P23

  STM for survey data

  Anna Linton  ·  Supervised by Paul Carroll

  The development of an R code for investigating the topics found in free text survey data using a technique that monitors both the content of the responses but also the metadata.

  RAP code Topic Modelling R

  Code Report

• P22

  Txt-Ray Align

  Dekai Zhang

  An investigation of extracting insight from multi-modal text and imaging data using contrastive learning.

  Multi-modal Contrastive Learning Python

  Code Report

• P21

  SynthVAE Continued

  David Brind

  Building on SynthVAE - focused on non-Gaussian input data, hyperparameter tuning, improving the codebase and starting to consider how fairness in the created data can be assessed and implemented.

  Synthetic Data VAE Python - PyTorch, Opacus

  Code Report

Wave 1 - April to September 2021

• P14

  Model Class Reliance

  Elizabeth Dolan

  Investigating the use of MCR to identify the value of including commercial sales data in respiratory predictions

  Model Explainability Commercial Data Python - mcrforest, SHAP

  Code Report

• P13

  NHS Text Data Exploration

  Beth Rushton-Woods

  Using a pre-defined toolset this project looked to understand how to ingest NHS.UK text data into a curated form.

  NLP Weak Supervison Python - scispaCy

  Code Report

• P12

  SynthVAE

  Dom Danks

  Initial creation of a variational autoencoder with differential privacy for generating single table tabular gaussian data.

  Synthetic Data VAE Python - PyTorch, Opacus

  Code Report

• P11

  SynPathDiabetes

  Tiyi Morris

  Exploration work into incorporating learning in to a pathway simulator for diabetes.

  Simulation Patient Pathways Python

  Code Report