Menu

Home / Directory / Professor Sheila M Bird

Professor Sheila M Bird

Contact information

Research interests

I have undertaken a series of record-linkage studies in respect of hard-to-reach populations in order to make discoveries about the public health (eg first quantification of high risk of drugs-related death soon after a) prison-release, and b) after hospital-discharge for those who have every injected) or to monitor the impact of public health policies (eg Scotland's National Naloxone Policy; Scottish Prison Service's adoption of opioid-substitution therapy as its healthcare standard). Record-linkage studies have also been the basis for quantifying the morbidity and mortality of Scotland's drug treatment clients or of injecting drug users who have been diagnosed with Hepatitis C virus. The latter - undertaken with Hutchinson and Goldberg - underpinned Scotland's Hepatitis C Action Plans (masterminded by Goldberg). Record-linkage studies (by others) have also been the platform for Bayesian capture-recapture estimation of the numbers of current injectors in Scotland (also in E&W). Most of my record-linkage work has been done in Scotland where - without exception - fact-of-death is registered within 8 days of death having occurred. This is not so in England and Wales where considerable registration delays occur in respect of deaths referred for inquest because, bizarrely, fact-of-death is not registered until cause of death is known. For over 5 years now, I have led the Royal Statistical Society's campaign for legislation to end the late registration of deaths in E&W. Until E&W counts deaths promptly and properly, its statistical system remains incompetent; and this incompetence delays the discovery potential from record-linkage studies. Confidentiality costs. There is a trade-off between the granularity of data that the analysis may wish to access and the degree of data-checking that can be undertaken and, on the other hand, the undoubted risk of deductive disclosure. In statistical modelling terms, we need to learn more about the inferential impact of this trade-off. The safe havens that the Farr Institute has set up are critical venues where such statistical investigations can be carried out. More recently, my research team has benefitted from the deployment (in consultation with us) of Natural Language Programming to dissect out information about daily methadone dose which, in methadone prescriptions, existed only in free-text but the free-text also included disclosive data: another warning for the careless in respect of care.data. These studies, quite properly, have required independent Privacy Access Committee or ethical approval. Such approvals can take longer to achieve than it takes to execute the statistical analysis plan that was written into the application. A better balance is needed but not at the expense of patient confidentiality.

Publications

About us

The Cambridge Centre for Data-Driven Discovery (C2D3) brings together researchers and expertise from across the academic departments and industry to drive research into the analysis, understanding and use of data science.

The Centre is funded by a series of collaborations with partners in business and industry which have an interest in using data science for the benefit of their customers and their organisations. Our founding partner is Aviva, the UK’s leading insurance company. We work with industrial partners to build a portfolio of collaborative research projects, provide professional development opportunities for their own staff and access to the full breadth and depth of the University’s talent pool in the area of data science.

With unprecedented access to increasing volumes of data, our research ranges from the underlying fundamentals in mathematics and computer science, to data science applications across all six University Schools of Arts and Humanities, Biological Sciences, Clinical Medicine, Humanities and Social Sciences, Physical Sciences, and Technology.

In parallel, our research addresses important issues around law, ethics and economics, in order to apply data science to solve challenging problems for society.

C2D3 supports collaboration and knowledge transfer in this growing field.

Join us.