Use this URL to cite or link to this record in EThOS:
Title: From data to knowledge in secondary health care databases
Author: Bettencourt-Silva, Joao
ISNI:       0000 0004 5346 7544
Awarding Body: University of East Anglia
Current Institution: University of East Anglia
Date of Award: 2014
Availability of Full Text:
Access from EThOS:
Access from Institution:
The advent of big data in health care is a topic receiving increasing attention worldwide. In the UK, over the last decade, the National Health Service (NHS) programme for Information Technology has boosted big data by introducing electronic infrastructures in hospitals and GP practices across the country. This ever growing amount of data promises to expand our understanding of the services, processes and research. Potential benefits include reducing costs, optimisation of services, knowledge discovery, and patient-centred predictive modelling. This thesis will explore the above by studying over ten years worth of electronic data and systems in a hospital treating over 750 thousand patients a year. The hospital's information systems store routinely collected data, used primarily by health practitioners to support and improve patient care. This raw data is recorded on several different systems but rarely linked or analysed. This thesis explores the secondary uses of such data by undertaking two case studies, one on prostate cancer and another on stroke. The journey from data to knowledge is made in each of the studies by traversing critical steps: data retrieval, linkage, integration, preparation, mining and analysis. Throughout, novel methods and computational techniques are introduced and the value of routinely collected data is assessed. In particular, this thesis discusses in detail the methodological aspects of developing clinical data warehouses from routine heterogeneous data and it introduces methods to model, visualise and analyse the journeys that patients take through care. This work has provided lessons in hospital IT provision, integration, visualisation and analytics of complex electronic patient records and databases and has enabled the use of raw routine data for management decision making and clinical research in both case studies.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available