Text analytics for healthcare

Code on a screenPart of NHS England’s digital transformation strategy is intended to increase patient self-management and enable prompt and appropriate advice and referral.  Our multi-disciplinary approach draws on the latest thinking in medical sociology and computer science to explore how machine learning and natural language processing can be harnessed to find new ways we can increase efficiency, improve outcomes and enhance patient experience. 

Ian Litchfield

Theme lead
Dr Ian Litchfield

Research Fellow

View profile

Dr Mark Lee

Theme lead
Dr Mark Lee

Senior Lecturer

View profile

 

Aims of the research

To investigate the application of Natural Language Processing technologies to improve all aspects of healthcare.

To develop automated methods for online consultation, diagnosis and triage. 

Meet the team

Dr Mark Lee (Theme lead)
Senior Lecturer, School of Computer Science
Interests in Natural Language Processing applications to healthcare; Sentiment analysis of patient feedback; Formal modelling of treatment of chronic conditions and multi-morbidity.

Dr Ian Litchfield (Theme lead)
Research Fellow, Institute of Applied Health Research, College of Medical and Dental Sciences

Dr Phil Smith
Interests in artificial intelligence for healthcare, in particular natural language processing, sentiment analysis and machine learning. 

Publications

P. Weber, J.B. Ferreira Filho, B. Bordbar, M. Lee, I. Litchfield, R. Backman (2018) Automated conflict detection between medical care pathways. Journal of Software: Evolution and Process 30.7

I. Litchfield, C. Hoye, D. Shukla, R. Backman, A. Turner, M. Lee, P. Weber.  (2018) Can process mining automatically describe care pathways of patients with long-term conditions in UK primary care?  A study protocol.  BMJ Open.

P. Weber, J. B. F. Filho, B. Bordbar, M. Lee, I. Litchfield and R. Backman.  (2017) Automated Conflict Detection Between Medical Care Pathways, Journal of Software: Evolution and Process, Special Issue: Software Engineering for Connected Health.

P. Smith & M. Lee (2016) “Sentiment Classification via a Response Recalibration Framework”  In the Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) held in conjunction with the Empirical Methods in Natural Language Processing conference (EMNLP) 2016.