HIC collaborative research projects
An example of HIC collaborative research projects
HT-ADVANCE: In ENSAT-HT we developed a machine learning predictor of hypertension from multi-omics data. In the 6-year, 14€m, EU HORIZON 2020 HT-ADVANCE project we will develop the predictor to be used by clinicians for clinical use and improve patient prognosis. In order to determine the performance three clinical trials, supported by TCTU at the University of Dundee, will be run to assess and improve the tools available in the clinic for identifying and treating hypertension.
SACRO and TRE-FX are two further DARE Driver Projects that we are Co-Investigators on for improving the capacity for trusted research environments (TREs) to disclosure control egress requests and federated analysis.
SMDH: The Smart Manufacturing Data Hub is a large, UK-wide initiative funded by Innovate UK to establish a novel data hub for SMEs to share and work with manufacturing data in a safe and secure environment. The Manufacturing Data Exchange Platform (MDEP) is underpinned by the TREEHOOSE TRE and the SMDH partners are part of the SATRE project team. A great example of growth and development of HIC research projects.
Data De-Identification: Patient records often include notes or short reports which are written by health professionals to help inform diagnosis or treatment. This information is called “unstructured data” as it provided as a simple block of text with no context. It is difficult to use for research as it is difficult to be sure that no identifiable information (e.g. names, dates) has been added unintentionally. This project, funded by Research Data Scotland, and led by DataLoch is investigating ways to train NLP to remove identifiable information to allow this useful data to be used for research.
ENSAT-HT: was an EU-funded Horizon 2020 research and innovation project that to investigate specific types of hypertension and whether it was possible to define specific profiles based on systems biology "-omics" approaches and subsequently use these to define more personalised approaches to disease management. A machine learning model was developed to differentiate between the three different types of Endocrine Hypertension: primary aldosteronism (PA), pheochromocytoma/functional paraganglioma (PPGL) and Cushing’s syndrome (CS).
P4Me: The P4Me initiative is a partnership between Precision Medicine and Pharmacotherapeutics Group at the University of Dundee and NHS Tayside. P4Me is developing the know-how for translation of Precision Medicine research into real world clinical implementation based on Prediction, Prevention, Personalisation, and Participation (P4). The programme incorporates the full spectrum of translational healthcare data science from genomics and imaging-derived biomarkers to remote eHealth solutions. A fundamental component of P4Me is the concept of self-learning healthcare systems whereby evidence of clinical utility is generated as a by-product of clinical activity using novel pragmatic trial designs and natural experiments.
Understanding the Causes of Diseases: This Health Data Research UK project aimed to understand disease at a deeper than ever biological level, to enable us to better predict the onset and progression of ill-health and tailor medicines for sub-types of disease (instead of a one-size-fits-all approach), as well as predict patients’ reaction to medicines. HIC researched how to enhance Trusted Research Environments (TREs) to support new multiomic data types including genomic and imaging data and also to provide High Performance Computing and GPU capabilities within the security controls of the TRE.
The Scottish Federated Safe Havens Project: This Health Data Research UK project researched different federated technological solutions to support the network to streamline processes and new capabilities for data discovery and access across the network. To learn about the network you may wish to read our recent paper. This work continuing with support from Research Data Scotland.
The Centre for Antimicrobial Resistance: The Centre for Antimicrobial Resistance at the University of Dundee brought together biologists, chemists, physicists, clinicians, mathematicians, epidemiologists, engineers and designers to focus on innovation in tackling antimicrobial resistance. For this project, HIC researched how to enhance Trusted Research Environments (TREs) to support new data types including analysis of bacterial genomic data and also to provide High Performance Computing capabilities within the security controls of the TRE.
Multimorbidity and clinical guidelines project: HIC researched the requirements for clinical guideline developers to understand the applicability of trial evidence to inform guideline development. A software tools was developed to enable users to compare the different characteristics of trial eligible and ineligible populations based upon real-world data.
The National COVID-19 Chest Imaging Database (NCCID) Project: NCCID is a centralised UK database containing chest X-ray (CXR), magnetic resonance imaging (MRI) and computed tomography (CT) images from hospital patients across the country. The database was created to support a better understanding of the COVID-19 virus and develop technology which will enable the best care for patients hospitalised with a severe infection. HIC have researched and developed a platform to extract the images from Scotland to include within this database.
The Cambridge Mathematics of Healthcare Hub: The Cambridge Mathematics of Information in Healthcare Hub (CMIH) is a collaboration between mathematics, statistics, computer science and medicine, aiming to develop robust and clinically practical data analytics algorithms for healthcare decision making. The work focusses on some of the most challenging public health problems; Cancer, Cardiovascular Disease, and Dementia. For this project HIC has researched and developed a prototype tool to embed a trained AI model within clinical systems for clinical validation.
The Scottish Improvement Science Collaborating Centre (SISCC): SISCC was a SISCC is a research collaboration that aims to bridge the gap between academia, public, practitioners and policy-makers to enhance quality, safety and person-centred care. In collaboration with ISD and other academic groups, HIC were involved in researching and developing prototype dashboards to help provide General Practitioners with the information they needed to monitor care and prescribing across all their patients.
Data standardisation using the OMOP common data model: This project researched how to convert data into the OMOP model for inclusion in the EHDEN project.
INSPIRED: The INSPIRED project was a 4-year partnership between two institutions, the University of Dundee’s Global Health Research Unit on Global Diabetes Outcomes Research and Madras Diabetes Research Foundation, between them command access to two of the most advanced diabetes management systems in the world. The project focused on building an extensive infrastructure to deliver precision medicine to improve outcomes in patients with diabetes in India. HIC researched TRE enhancements to support genomic data analysis at scale within such environments.
Graph Based Data Federation for Healthcare Data Science: This Health Data Research UK sprint project researched different methods for mapping ontologies including graphical representations.
Application of AI to Heart Failure: In a collaboration between the School of Medicine, UMC Groeningen, National Heart Centre Singapore, US2.ai and Roche we identified data-driven ways to improve the diagnosis of heart failure from echocardiograms.
Contact Dr Christian Cole directly regarding collaborating with us