果冻影院

Development of a point-of-care microfluidics platform to monitor kidney transplant rejection听

This project will develop a novel point-of-care device for monitoring kidney transplant patients.

For patients with end-stage kidney disease, transplants offer substantial benefits. Unfortunately, however, the long-term function of kidney transplants hasn鈥檛 improved by much over the last 20 years 鈥� around 40% of transplanted kidneys fail within a decade. The main cause of long-term transplant failure is rejection by the patient鈥檚 immune system.

The current method for monitoring transplant patients involves looking at their serum creatinine levels, however, this technique isn鈥檛 sensitive enough to detect early-stage rejection. This team鈥檚 device will look at urinary chemokines 鈥� small protein molecules produced by inflammatory cells. These are some of the most potentially useful markers in patients at risk of transplant rejection.听

Project team:
鈥⑻�听 听PI: Dr Manish K Tiwari, Professor of Nanoengineering, 果冻影院听
鈥⑻�听 听Mr Reza Motallebzadeh, Associate Professor, 果冻影院 & Consultant Renal Transplant Surgeon, Royal Free Hospital听
鈥⑻�听 听Dr Stavroula Balabani, Professor of Fluid Mechanics, 果冻影院听
鈥⑻�听 听Dr Mark Harber, Consultant Renal Transplant Nephrologist, Royal Free Hospital

Image Quality Control for PACS-integrated quantitative neuroradiology听

This project will produce a state-of-the-art artificial intelligence system to detect image quality issues in MRI brain scans.听

MRI brain scans are used by clinicians to help diagnose conditions such as dementia and epilepsy. Sometimes, however, image quality can adversely affect this decision-making process. This system would alert clinicians to image quality issues and their severity, to help them decide whether further scans are needed for听improved diagnosis.

The system will use existing brain MRI datasets from 果冻影院 and the National Hospital for Neurology and Neurosurgery that have already been assessed for image quality. The team鈥檚 hope is that in the future this could be extended to other conditions beyond dementia and epilepsy.

Project team:
鈥⑻�听 听PI: Dr Sjoerd Vos, Lecturer in Quantitative Neuroradiology
鈥⑻�听 听Prof Tarek Yousry, Professor of Neuroradiology听
鈥⑻�听 听Dr Gary Zhang, Reader in Computational Imaging

Leveraging the potential of advanced machine learning techniques to support clinical decision-making during emergency transport of critically ill children to paediatric intensive care

This project aims to help clinicians see signs of deterioration in sick children more quickly by applying machine learning techniques to ICU data.听

Seriously ill children in the UK are transported from general hospitals to specialist paediatric intensive care units by retrieval teams, who provide 鈥榤obile intensive care鈥� en route and monitor their vital signs.听

The Children鈥檚 Acute Transport Services team at Great Ormond Street Hospital is the first retrieval service to implement software that collects and stores high-resolution physiological data. With data from over 2,000 children, this is a significant resource to apply machine learning techniques and discover signs that predict the child鈥檚 illness trajectory.听

This project will create preliminary models to accurately identify children at high-risk and those likely to respond to specific treatments.听

Project team:
鈥⑻�听听听PI: Dr Kezhi Li Lecturer, AI in Healthcare听
鈥⑻�听听听PI: Dr Padmanabhan Ramnarayan Consultant in Paediatric Intensive Care & Retrieval听
鈥⑻�听听听Prof Christina Pagel, Professor of Operational Research
鈥⑻�听听听Prof Mark Peters, Professor in Paediatric Intensive Care Medicine听
鈥⑻�听听听Dr Thomas Monks, Associate Professor of Health Data Science

Living with Prostate Cancer: Pro Care Zone: a digital prostate cancer support tool which builds on patients鈥�, their carers鈥� and health care professionals鈥� participation to improve their experience and clinical outcomes in cancer care听

Prostate cancer is the most common cancer in the UK 鈥� more than 130 men are diagnosed every day.听

Specialist treatments like surgery are performed at specialist hospitals, such as 果冻影院H, and supportive care is delivered across local hospital networks. While this model improves patient outcomes, it can lead to confusion about who they need to see, where and what for. It can also cause problems with travel, missed appointments and a poor patient experience.听

For specialist healthcare professionals who deliver these treatments, it can lead to an increased workload and low job satisfaction.听

This project will develop a web and app 鈥榙ashboard鈥� tool to support patients with prostate cancer, their carers and healthcare professionals. The digital health intervention will improve communication between groups, and provide informational and emotional support. 听It builds on a similar tool that was successfully piloted for oesophageal cancer patients.听

Project team:
鈥⑻�听听听PI: Dr Patricia Schartau, Academic Clinical Lecturer in Primary Care and GP听
鈥⑻�听听听Prof Ann Blandford, Deputy Director (Digital Health) 果冻影院 Institute of Healthcare Engineering
鈥⑻�听听听Prof Elizabeth Murray, Deputy Director (Clinical), 果冻影院 Institute of Healthcare Engineering; Professor of eHealth and Primary Care; Co-director of the eHealth Unit