The London School of Hygiene & Tropical Medicine (LSHTM)

The London School of Hygiene & Tropical Medicine (LSHTM) invites functions for a cutting-edge doctoral analysis alternative exploring how Large Language Models (LLMs) can remodel the way in which advanced illnesses are recognized in large-scale Electronic Health Record (EHR) databases.

This venture addresses one of essentially the most urgent challenges in fashionable well being information science: creating correct, clear and environment friendly strategies for phenotyping—the method of figuring out affected person teams with particular illnesses or circumstances from routine scientific information. With scientific datasets increasing quickly, AI-driven approaches provide the potential for main advances in epidemiological analysis.

Facilitating Complex Phenotyping for Electronic Health Records Using Large Language Models  MRC London Intercollegiate Doctoral Training Partnership (MRC LID) Studentship
Project out there for 2026/27 entry
Full-time or Part-time

---

Supervisory Team

Primary Supervisor
Dr Julian Matthewman, LSHTM
Faculty of Epidemiology & Population Health
Department of Non-communicable Disease Epidemiology
Email: julian.matthewman@lshtm.ac.uk

Co-Supervisor
Professor Sinéad Langan, LSHTM
Faculty of Epidemiology & Population Health
Department of Non-communicable Disease Epidemiology
Email: sinead.langan@lshtm.ac.uk

---

Project Overview

Accurate identification of sufferers with advanced circumstances inside EHR methods is crucial for high-quality epidemiological analysis. Traditional phenotyping strategies rely closely on handbook professional interpretation and are sometimes troublesome to scale—notably for illnesses involving subtypes, diagnostic uncertainty, or multifaceted scientific histories.

This PhD venture will examine how Large Language Models—with their capability to course of and interpret huge quantities of scientific data—can improve and speed up phenotyping workflows. The profitable candidate will develop a clear, reproducible framework for LLM-assisted phenotyping and apply it to create an Atlas of Complex Disease Phenotypes utilizing the UK’s CPRD Aurum main care database.

The work will generate a novel methodology of broad worth to the well being information science group, demonstrating the sensible impression of superior AI applied sciences on epidemiological analysis.

---

Key Objectives

1. Review the present panorama of LLM functions in scientific classification and phenotyping, together with the event of a dwelling scoping evaluate.

2. Design a reproducible framework integrating scientific experience with LLM-derived insights for high-quality phenotyping.

3. Apply and validate the framework by creating phenotype definitions for a spread of advanced illnesses in CPRD Aurum—doubtless inside pores and skin or inflammatory illness areas, relying on candidate and supervisor experience.

4. Evaluate epidemiological metrics (e.g. incidence, prevalence) produced utilizing the brand new LLM-derived phenotypes and examine them with established strategies.

---

Skills You Will Develop

• Large Language Model analysis, immediate design and fine-tuning

• Electronic Health Record information administration and evaluation

• Epidemiological study design and interpretation

• Quantitative evaluation utilizing R or Python

• Natural Language Processing strategies for scientific textual content

• Reproducible analysis and open science practices

This venture aligns with MRC LID themes in Health Data Science, Translational & Implementation Research, and Global Health.

---

Data Resource

You will work primarily with CPRD Aurum, a complete UK main care dataset with linkages to hospital data and different well being information sources. It consists of diagnoses, signs, prescriptions, referrals and take a look at outcomes.

---

Eligibility & Entry Requirements

Applicants should meet LSHTM’s commonplace doctoral eligibility standards and will reveal:

• A powerful quantitative background and health-related coaching

• A Master’s diploma in epidemiology, well being information science, medical statistics, or a associated subject

• Proficiency in Python or R

---

Study Format & Location

• Full-time: Yes

• Part-time: Yes

• Primary location: LSHTM, Bloomsbury, London

• Travel necessities: None past commonplace convention attendance (as much as three throughout the studentship)

Students funded by means of MRC LID are anticipated to work usually on web site.

For extra data click on here

For extra alternatives, Click HERE

Related