Enriching function and disability data with natural language processing

More than one in six people around the world is disabled, and this number is expected to increase dramatically over the coming decades as longer lifespans and global ageing contribute to the rise of multiple chronic conditions with disabling impacts. People with disabilities often experience complex limitations in everyday function, which frequently negatively impact the ability to fully participate in everyday aspects of society. Functional limitations are an essential part of the lived experience of health, but they are highly complex and individual to each person, arising from dynamic interactions between health conditions, body functions, and personal and environmental factors. A shared understanding of the experience of function and disability, and the multiple factors that shape that experience, is therefore critical to delivering personalised healthcare that responds to the needs and priorities of distinct individuals. However, information on function is often poorly recorded in health data and difficult to analyse due to its complexity, limiting the ability of healthcare professionals to take this information into account.

Artificial intelligence technologies have significant potential to help leverage information on function as a key part of better-informed and person-centred healthcare. The flexibility of AI technologies is invaluable for analysing the dynamic and complex nature of human function, and for combining the multiple data sources and modalities required to effectively capture a holistic picture of functioning in practice. Natural language processing (NLP) techniques have particular value in analysing information on function, as the multiple factors that affect function and the lack of standardised measurements means function is often documented only in free text medical records. Early research has demonstrated clear potential in NLP methods to extract and analyse information on function from free text data, helping to enrich common clinical measures of function and widen data analysis to include patients who are not able to access specialised rehabilitation care. However, these methods have had only limited application and have not yet been applied systematically to real-world healthcare records or combined with structured clinical measures.

This project will bring NLP methods for function into greater readiness for application in real healthcare settings. It will address key technological innovations as well as clinical application challenges, including:

• Developing NLP models that reflect the sentence-level syntactic and semantic complexity of information on functional activity and participation;
• Designing content-driven strategies for evaluating the quality of functional status information extraction;
• Comparing the relative benefits of NLP-based analysis of information on function with manual, expertise-based linking to functional activity categories;
• Exploring strategies for jointly analysing information on function in unstructured free text together with structured clinical measures for more robust data-driven understanding of functional status.

Interested candidates are encouraged to contact the project supervisor (Dr Denis Newman-Griffis, [email protected]) to discuss your interest in and suitability for the project prior to submitting your application. 

Supervisor Bio

Dr Denis Newman-Griffis is AI for Health Lead in the Centre for Machine Intelligence and a Senior Lecturer in Computer Science at the University of Sheffield. Their research interests are in natural language processing and representation learning for healthcare, AI and disability, and responsible AI.

Candidate Requirements

• Masters degree in a relevant subject field, computer science, health informatics, or computational linguistics (2(i) / Merit or higher).
• An interest in natural language processing and rehabilitation and disability. Candidates with relevant research experience will be preferred.
• If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0 in each component.

About the Department/Research Group

Supported by a multi-million pound investment from the University of Sheffield, the Centre for Machine Intelligence is a strategic initiative dedicated to the transformation and acceleration of our research, innovation and teaching via Artificial Intelligence (AI).

99 percent of our research is rated in the highest two categories in the REF 2021, meaning it is classed as world-leading or internationally excellent. We are rated as 8th nationally for the quality of our research environment, showing that the Department of Computer Science is a vibrant and progressive place to undertake research.

The host School for the successful candidate will confirmed on offer.

How to Apply

To apply for a PhD studentship, applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form. Make sure you name Dr Denis Newman-Griffis as your proposed supervisor.

Information on what documents are required and a link to the application form can be found here – https://www.sheffield.ac.uk/postgraduate/phd/apply/applying 

The form has comprehensive instructions for you to follow, and pop-up help is available. 

Your research proposal should:

• be no longer than 4 A4 pages, include references
• outline your reasons for applying for this studentship
• explain how you would approach the research, including details of your skills and experience in the topic area