Addressing patient mortality in hemodialysis via AI applied to metabolomics and material science

Approximately 2 million individuals globally suffer from kidney failure, necessitating treatment options such as transplantation and dialysis. Transplantation is limited by donor availability, forcing many to rely on HD. Whereas transplant recipients exhibit approximately 80% survival rates five years post-procedure, those undergoing HD have less than a 50% chance of surviving the same period due to what's known as “residual uremic syndrome” resulting from the incomplete removal of certain uremic toxins during HD, significantly contributing to the higher mortality observed in these patients.

Current HD technologies rely on membranes which are limited by size, thus unable to effectively eliminate larger uremic toxins from the patient's bloodstream. This approach lacks precision and effectiveness as it is designed on small molecules like urea and fails to address other, more harmful toxins.

The first crucial step is to clearly identify the metabolites associated with adverse effects. This task can be addressed using a combination of metabolomics and AI. Metabolomics can detect a wide range of metabolites, some of which may play critical roles in the health outcomes of patients with kidney failure.

Three studies have investigated the link between serum metabolites and mortality in patients with kidney disease, but they have yielded inconsistent results regarding which metabolites are implicated, underscoring the need for further research. The integration of metabolomics with AI may also enhance our understanding of the mechanisms: this deeper insight is essential for developing more effective HD treatments that can mitigate the adverse effects. A comprehensive AI-based analysis of the existing data is essential, laying the groundwork for future large-scale metabolomics research. However, identifying these metabolites is just the initial step. The ultimate goal is to leverage this information to enhance dialysis treatments by developing materials capable of efficiently capturing the most toxic molecules. AI has the potential to expedite the exploration of the vast materials space. Achieving both the identification of harmful metabolites and the development of effective materials is an ambitious task, given the multitude of toxins and materials involved.

Fortunately, AI technologies can greatly accelerate progress towards these dual objectives.

https://www.bbc.com/news/uk-scotland-edinburgh-east-fife-67156562

Such study will allow to correlate specific materials features (e.g. chemical composition and porosity descriptors) to the ability of the filtering materials of removing toxic molecules correlated to mortality. This work will provide guidelines for material synthesis and/or selection in the design of more efficient and tailored HD treatment which can reduce patients’ mortality.

References: [1] The Kidney Project, University of California San Francisco, https://pharm.ucsf.edu/kidney [2] S. Al Awadhi et al, A Metabolomics Approach to Identify Metabolites Associated With Mortality in Patients Receiving Maintenance Hemodialysis, Kidney Int Rep 2024 9, 2718–26. [3] S. Kalim et al., A Plasma Long‐Chain Acylcarnitine Predicts Cardiovascular Mortality in Incident Dialysis Patients, J American Heart Association 2, 2013. [4] Hu, J.-R., et al Serum Metabolites and Cardiac Death in Patients on Hemodialysis, Clin J Am Society of Nephrology 14(5): 747-749, 2019. [5] https://nurturebiobank.org/, visited on 4th October 2024 [6] T. Fabiani et al., In silico screening of nanoporous materials for urea removal in hemodialysis applications, Phys. Chem. Chem. Phys., 2023, 25, 24069. [7] REDIAL, redefining hemodialysis with data-driven materials innovation, project https://www.suspromgroup.eng.ed.ac.uk/redial

https://www.suspromgroup.eng.ed.ac.uk/redial

https://www.ai4biomed.io/research/projects-2025/#cmsm

https://www.ai4biomed.io/

Application deadline: 20 January 2025

We offer fully funded 4-year studentships, covering tuition fees, stipend (£19,237 in 2024/25) and an individual budget for travel and research costs. There are also allowances for sick pay, maternity leave and other purposes. Funding has open eligibility regardless of your nationality and domicile.

The CDT offers additional funding for public engagement activities, evaluation experiments and research visits.

Each student will also benefit from state-of-the-art facilities, including unique data and computational resources. The CDT has access to EPCC facilities including the University’s HPC Centre of excellence offering unique AI capability (Cerebras CS-1/CS2, Graphcore Bow Pod), supercomputing (ARCHER2, DiRAC, Cirrus), and analytics platforms, assisted by over 100 technology experts. EIDF will provide research compute capacity for AI via a new cluster of 136 Nvidia A-100 GPU cards.

The University of Edinburgh is committed to equality of opportunity for all its staff and students, and promotes a culture of inclusivity. Please see details here: https://www.ed.ac.uk/equality-diversity

Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree. Further information on English language requirements for EU/Overseas applicants.

Tuition fees + stipend are available for Home/EU and International students

CDT AI in Biomedical Innovation Conditions

We offer fully funded 4-year studentships, covering tuition fees, stipend (£19,237 in 2024/25) and an individual budget for travel and research costs. There are also allowances for sick pay, maternity leave and other purposes. Funding has open eligibility regardless of your nationality and domicile.

The CDT offers additional funding for public engagement activities, evaluation experiments and research visits.

Each student will also benefit from state-of-the-art facilities, including unique data and computational resources. The CDT has access to EPCC facilities including the University’s HPC Centre of excellence offering unique AI capability (Cerebras CS-1/CS2, Graphcore Bow Pod), supercomputing (ARCHER2, DiRAC, Cirrus), and analytics platforms, assisted by over 100 technology experts. EIDF will provide research compute capacity for AI via a new cluster of 136 Nvidia A-100 GPU cards.

Further information and other funding options.