Research Associate in Machine Learning Applied to Electronic Health Records - Strand, London, WC2R 2LS

Research Associate in Machine Learning Applied to Electronic Health Records - Strand, London, WC2R 2LS

About us

This project is led by a collaboration between a university and a large university hospital. The School of Neuroscience at King’s College London is the second largest university neuroscience department in the UK, with approximately 100 faculty and a total of 600 staff and students. The School holds approximately £220 million in currently-active research grants, and, out of all universities globally, has the 4th highest number of highly-cited publications in neuroscience (source: SciVal 2022). The regional Neurology and Neurosurgery service is located in King’s College Hospital on the same campus, and, including stroke and neurorehabilitation, has approximately 200 inpatient beds, making it one of the largest and busiest such centres in the UK. King’s College Hospital is home to the largest EEG department in the UK and one of the busiest epilepsy specialist services.

Epilepsy is a common disorder affecting 1% of the population. About a third of all people with epilepsy do not respond to any treatment, and have reduced quality of life, increased morbidity, increased mortality, and substantial healthcare costs. Hitherto, attempts to identify predictors of refractoriness have predominantly examined very few candidate predictors identifiable from limited hand-curated datasets. In this project, we aim to predict treatment outcome in epilepsy using very large EHR datasets. Real world data in EHRs includes extensive and rich detail about the presentation, phenotype, investigations, diagnosis, comorbidities, treatments, encounters with hospital services, and clinical outcomes for very large numbers of patients with epilepsy. We propose to use our open-source EHR database processing and NLP AI data pipeline and toolset to extract this EHR information and structure it. Once in this interoperable standardised format, we will then employ novel AI tools for predictive analytics to identify risk factors for treatment-resistant epilepsy. Our predictive models will be tested and validated across epilepsy populations in several large NHS Trusts and will be deployable in any NHS Trust with access to the open-source NLP suite of tools.

About the role

This exciting research role will be responsible for helping to continue the successful delivery and future development of ongoing epilepsy research projects funded by the UK Epilepsy Research Institute, Medical Research Council and Angelini Pharma. The Research Fellow will use a range of Data Science skills — including Artificial Intelligence (AI), Natural Language Processing (NLP) methods with a special focus on generative Large Language Models (LLMs), as well as Machine Learning (ML) tools — to interrogate a very large sample of Electronic Health Records from people with epilepsy across multiple NHS hospitals. They are expected to have experience working in Data Science, but not necessarily in a health-related field. They will also help to further develop ML models to predict patients’ clinical outcomes.

This is a full-time post, and you will be offered an a fixed term contract until 31st March 2027.

Research staff at King’s are entitled to at least 10 days per year (pro-rata) for professional development. This entitlement, from the Concordat to Support the Career Development of Researchers , applies to Postdocs, Research Assistants, Research and Teaching Technicians, Teaching Fellows and AEP equivalent up to and including grade 7. Visit the Centre for Research Staff Development for more information.

About you

To be successful in this role, we are looking for candidates to have the following skills and experience:

Essential criteria

1.  PhD qualified in relevant subject area (e.g. data science, computer science, AI/NLP)*
2. Experience in Data Science techniques, especially data analysis and prediction modelling, evidenced by publications and/or dissertation, or equivalent evidence of expertise and completed research outputs
3. Understanding of AI and, especially, deep learning techniques, with a demonstrable understanding of LLMs
4. Proven ability to write code in Python
5. Experience working in a research environment
6. Excellent writing and communication skills, including the ability to communicate technical concepts to a non-technical audience

Desirable criteria

1. Experience working with NHS data or other medical data
2. Experience working with text data
3. Demonstrable knowledge of ML Ops
4. Good knowledge of best practices in data analysis in Python 

Downloading a copy of our Job Description

Full details of the role and the skills, knowledge and experience required can be found in the Job Description document, provided at the bottom of the page. This document will provide information of what criteria will be assessed at each stage of the recruitment process.

* Please note that this is a PhD level role but candidates who have submitted their thesis and are awaiting award of their PhDs will be considered. In these circumstances the appointment will be made at Grade 5, spine point 30 with the title of Research Assistant. Upon confirmation of the award of the PhD, the job title will become Research Associate and the salary will increase to Grade 6.