Louise Aubiniere-Robb

Dr Louise Aubiniere-Robb is a Clinical Research Training Fellow collaborating with industry partner Optum. Her project will use artificial intelligence and machine learning with real-world healthcare data and digital health solutions to systematically identify people at high rist of chronic Kidney Disease progression, kidney ffailure and cardiovascular complications.

When did your Fellowship start and how long will it last?

My MRC Medicines Development Fellowship will start in October 2025 and will last three years.

What were you doing prior to your Fellowship.

I am a nephrology registrar, training in the West of Scotland. Before starting my Fellowship, I will be working in the renal unit at the Queen Elizabeth University Hospital in Glasgow.

Why did you choose this Fellowship Programme?

I chose this Fellowship because it offers a unique opportunity to combine structured academic training, industry collaboration, and real-world impact. It aligns perfectly with my long-term goal of becoming an academic leader in AI-enabled nephrology. It provides protected time, expert mentorship and training, and the opportunity to work at the intersection of machine learning, digital health, and nephrology – all of which I believe are crucial for advancing preventative care in chronic kidney disease (CKD).

What is the aim of your research?

The aim of my research is to address the growing burden of CKD by improving how preventative, guideline-based treatment is delivered earlier in the disease course. By integrating AI and machine learning with real-world healthcare data and digital health solutions, my project aims to systematically identify people at high risk of CKD progression, kidney failure and cardiovascular complications.

A central objective is to develop and validate an AI-driven clinical decision support tool that can screen health records, identify gaps in prescribing, and help clinicians optimise the use of recommended therapy. This research will also investigate variations in care delivery, with particular attention to socioeconomic disparities in prescribing patterns, to generate evidence that can inform targeted strategies for improving equitable access to guideline-recommended treatment.

By using statistical simulation techniques to model the long-term impact of this tool on renal, cardiovascular, and care process outcomes, my research aims to demonstrate how digital innovations can help shift the NHS from a predominantly reactive approach to CKD management to a more proactive, preventative model of care. My long-term goal is to enable earlier intervention, reduce the risk of cardiovascular events and progression to end-stage kidney disease, and ultimately reduce future demand for costly treatments such as dialysis and transplantation.

What inspired you to look at this field?

As a nephrology trainee, I see first-hand the impact of late diagnosis and missed opportunities in CKD management. Despite major advances in treatment, many people still progress to kidney failure or experience preventable cardiovascular complications. I am passionate about finding new ways to close this gap in treatment and care, and I believe carefully designed AI and digital health tools offer huge potential to support personalised treatment and early intervention in people with CKD. This project combines my clinical experience with my growing expertise in data science to tackle a problem that urgently needs innovative solutions.

Which industry partner are you working with and how will they support you in achieving your goals? What will your partner gain from working with you?

I am working with Optum, a leading digital health company with expertise in population health management and clinical decision support. Optum will provide access to their digital platform, which I will adapt to integrate my guideline-based, AI-driven care pathway and predictive models designed to identify high-risk CKD subgroups and treatment opportunities to help clinicians proactively optimise medication use. Optum’s technical and software development support will help translate this research into a practical clinical tool that can be tested at scale, with the future aim of live deployment in primary care settings. In return, Optum will gain a robust, evidence-based solution to modify and enhance their existing product, co-designed with academic rigour and real-world clinical insight. This will strengthen its clinical relevance and increase its potential for wider adoption into routine care pathways.

Why did you choose Optum as your HEI partner?

I chose Optum because they have an established track record in delivering digital health solutions within primary care settings. Their products are already integrated in parts of the UK healthcare system, giving my project a realistic pathway to future implementation. Optum brings extensive expertise in data security, coding, and analytics, all of which are vital to ensure the clinical tool I develop is both robust and practical for real-world use. Working with Optum will also give me unique insights into how academic research can be translated into scalable, NHS-ready digital health technologies.

What do you plan to do when you have completed your Fellowship?

By the end of this Fellowship, I will have developed and validated a clinical decision support tool to identify people with CKD who would benefit from treatment optimisation and early intervention. After completing this Fellowship, I plan to pursue an Intermediate Fellowship to move from tool development to real-world implementation. I aim to deploy and test the tool prospectively in primary care settings and carry out an implementation study. Building on this, I plan to expand the model to include multimorbidity and multi-outcome prediction, and to lead research that integrates robust, explainable AI into everyday kidney care. Long term, I want to build a research programme as an academic nephrologist that drives innovation in preventative nephrology, improves patient outcomes, and helps the NHS leverage data and technology in smarter, more equitable ways.