Publications

Important clinical information is recorded in free text in patients’ records, notes, letters and reports in healthcare settings. This information is currently under-used for health research and innovation. Free text requires more processing for analysis than structured data, but processing natural language at scale has recently advanced, using large language models. However, data controllers are often concerned about patient privacy risks if clinical text is allowed to be used in research.

We present a prototype solution for improving transparency and quality assurance of the data linkage process through data provenance tracking designed to assist Data Analysts, researchers and information governance teams in authenticating and auditing data workflows within a Trusted Research Environment (TRE).

Manual data annotation of information related to geriatric syndrome (GS), which includes various conditions affecting older adults, is required to train machine learning (ML) models to classify patients’ health data for information that is otherwise poorly coded in structured electric health records. Such classification can be highly beneficial to support patients’ healthcare in several ways, including early detection and diagnosis of geriatric syndrome, improving healthcare practices and patient empowerment and education (leading to improved adherence to treatment plans and bett...

This project focused on delivering semi-automated tools and exploring approaches to improve two areas of risk assessment and monitoring: Data provenance, improving the trustworthiness of data ingestion, processing and linking, making sure it is compliant for research; and Privacy assessment, minimising the risk of identifiable information in clinical free-text records (e.g., GP letters, discharge summaries). Public Involvement and Engagement (PIE) were central to our project by ensuring risks were properly identified and addressed, public perspectives were embedded into our outco...

Background: Following myocardial infarction (MI), therapies are recommended that reduce risk and prevent future cardiovascular events. Trends in the provision of guideline-directed medical therapies by sex, age, ethnicity and socioeconomic deprivation status may help identify opportunities to reduce inequalities in post-MI care.

Dementia diagnoses are captured across multiple routine data sources, but discrepancies between these may affect both care and research. This study determined the prevalence and overlap of recorded dementia across primary care, hospital and community prescribing data in a UK regional cohort, and examined whether outcomes differed by the setting in which dementia was first recorded.

Background: The role of high-sensitivity cardiac troponin (cTn) assays for children and young adults is uncertain, and no guidance is available on diagnostic thresholds. This study evaluates the effect of applying pediatric compared to adult upper reference limits (URLs) for cTn.

Objective: To evaluate the impact of transitioning from a high-sensitivity assay measuring cardiac troponin I to one measuring cardiac troponin T on the care and outcomes of consecutive patients with suspected acute coronary syndrome.