Skip to main contentSkip to footer
Dark screen with yellow blue and white abstract code written over it
Brighton & Sussex Medical School

ARC KSS Data Science Hub

ARC KSS Data Science Hub

Welcome to the ARC KSS Data Science Hub!

An open access resource, identifying and exploring national and regional (Kent, Surrey and Sussex) health and social care datasets. A space where data access barriers are addressed, in the hope of encouraging improved healthcare based on the real needs of everyday people as users of health and care services.

Medical professional sitting at a table with graphics and images representing medical data scattered across them

About this resource

98% of the UK population are registered with an NHS GP practice, providing a wealth of data and information about interactions with health and social care provisions. This data, which is captured in routine datasets (except where somebody has actively opted out), has the potential to save lives – it allows health care services to be evaluated, health needs and inequalities to be recognised and addressed, and important health improvement projects to be developed based on need.

Whilst the data provides so much hope and potential for better health and wellbeing, confusing data access arrangements mean that those who could analyse the data to inform change and improvement, can’t. Often, analysts are unable to access this vital information in a timely way, meaning the data goes unused and is abandoned.

We recognise the challenges faced by researchers wanting to use routinely collected health and social care data to build understanding and improve healthcare services, and in response have developed this resource - the ARC Data Science Hub. The team hopes this resource provides guidance and clarity, eliminating the fog of confusion around national and regional datasets and helps unlock their full potential for greater, public good.

 

To note: The ARC Data Science Hub has been built in collaboration with the National Institute for Health and Care Research (NIHR) Applied Research Collaboration Kent, Surrey and Sussex (ARC KSS) funded project:

Development of data governance, methods, and training resource to support ARC-wide data analysis of routinely collected health and social care data.

The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care.

 

NIHR KSS logo

Datasets

Here you will find information about both national and regional datasets, along with resource packs containing information on access pathways, costs, training requirements, user access agreements and more. Where possible, we have included a data dictionary for the dataset so that you can explore what each dataset holds and decide whether it is an appropriate data resource for your research.

If you’d like to speak to the team for further guidance, join one of our fortnightly Data Hub Clinics!

National Datasets >

Regional Datasets >

KMS Secure Data Environment

The NHS Research Secure Data Environment (SDE) is made up of 12 SDEs, providing secure access to healthcare data for research and innovation, without the need for the data to leave its existing environment. SDEs for research are data access and storage platforms which uphold the highest standards of privacy and security of NHS health and social care data when used for research and analysis.

Learn more about KMS SDE >

BACKGROUND IMAGE FOR PANEL

Data hub clinics

The ARC Data Hub team are running fortnightly Data Hub Clinics via Teams. The clinics are an opportunity to speak to the team about your data needs and explore together the data access pathway for the specific dataset you would like to use for your research.

To book a 30-minute slot please contact us with the details of your query unlockingdata@bsms.ac.uk

BACKGROUND IMAGE FOR PANEL

Talking to the public about data

As a team we recognise the need for transparency with the public about how their health data is used and handled. A recent project called Unlocking Data explored public view and perception of health data being used for research through holding public discussion groups. The findings were then reported back to Kent and Sussex dataset controllers, advising them on how to be clear and trustworthy about data use. Results highlighted the importance of public involvement to build trust and transparency.

The short video below features researchers and participants from the Unlocking Data project discussing their views about sharing their health data and what it means to them.


The Unlocking Data team shared the research results from their project in April 2022. The event was aimed at those who were part of the project, participated in discussions, and those interested in sharing health data. You can watch a recording from the event below.


You can find out more information about the Unlocking Data Project here.

BACKGROUND IMAGE FOR PANEL

News, publications and events

Find out more about our work, presentations, news, publications and collaborations.

Recent publications

Understanding how to build a social licence for using novel linked datasets for planning and research in Kent, Surrey and Sussex: results of deliberative focus – view it here >

Ethical issues when using digital biomarkers and artificial intelligence for the early detection of dementia –  view it here > 

Challenges Encountered and Lessons Learned when Using a Novel Anonymised Linked Dataset of Health and Social Care Records for Public Health Intelligence: The Sussex Integrated Dataset – view it here >

Blog

The ARC KSS Data Science Hub blog is regularly updated with new content covering the latest developments and news in health data science.

Read our latest blog post >

BACKGROUND IMAGE FOR PANEL

Papers of interest

Promising algorithms to perilous applications: a systematic review of risk stratification tools for predicting healthcare utilisation – view it here >

Targeted validation: validating clinical prediction models in their intended population and setting – view it here >

The human role to guarantee an ethical AI in healthcare: a five-facts approach – view it here > 

The value of standards for health datasets in artificial intelligence-based applications – view it here >

Five critical quality criteria for artificial intelligence-based prediction models – view it here >

Mapping and evaluating national data flows: transparency, privacy, and guiding infrastructural transformation – view it here > 

Concept libraries for automatic electronic health record based phenotyping – view it here >

Characterizing and Managing Missing Structured Data in Electronic Health Records: Data Analysis – view it here >

Informative missingness in electronic health record systems: the curse of knowing – view it here > 

Strategies for handling missing data in electronic health record derived data – view it here >

Accounting for missing data in statistical analyses: multiple imputation is not always the answer – view it here >

Sick patients have more data: the non-random completeness of electronic health records – view it here >

There is no such thing as a validated prediction model – view it here > 

Rethink reporting of evaluation results in AI – view it here >

Learning from data with structured missingness – view it here > 

Secondary use of routinely collected administrative health data for epidemiologic research: Answering research questions using data collected for a different purpose – view it here >

Contact us

For any further information about the ARC Data Science Hub or the project, please contact the team at unlockingdata@bsms.ac.uk