Our Research.
Transforming cutting edge research into practical, tangible solutions.
See our latest peer-reviewed publications, global conference presentations, and in-progress journal submissions across artificial intelligence, computer science and operations research.
Conference
Presented · 2025
Recognizing Cardiovascular Risk Patterns using Ensemble Learning Techniques
This work investigates cardiovascular risk prediction using ensemble machine learning techniques. It evaluates multiple ensemble models to improve prediction accuracy and support early clinical decision-making.
- Venue: 8th International Conference on Recent Trends in Image Processing & Pattern
- Recognition (RTIP2R), Marrakech, Morocco, 11–13 December 2025
Conference
Presented · 2025
Enhancing Kidney Transplant Compatibility Outcomes through Graph Attention-Based Learning
This research proposes a Graph Attention Network-based framework for modelling donor–recipient relationships. The objective is to improve compatibility assessment by learning complex interactions among transplant variables.
- Venue: ICA2S 2025, UAE, 13–14 November 2025
- In collaboration with Ajman, Gulf Medical University
Conference
Presented · Presented Online (9-12 June 2026)
Leveraging Federated Learning for Predicting Kidney Graft Survival Using OPTN Dataset
The paper presents a federated learning approach for kidney graft survival prediction using the OPTN dataset. The work emphasizes privacy-preserving collaborative learning without sharing patient-level data.
- Venue: FLICS 2026
- Hybrid · IEEE Spain Section Technical Co-sponsorship
Journal
Under Review · Expected 2026
Modeling Kidney Transplant Compatibility using a Federated Multi-Layer Perceptron Framework
This study develops a federated multilayer perceptron framework for kidney transplant compatibility prediction.
- Venue: Telematics and Informatics Reports (Elsevier)
- CiteScore 6
- Impact Factor 9.9
Journal
In Progress · Submission Planned (July 2026)
Survey Paper on Federated Learning in Healthcare
This comprehensive survey reviews federated learning architectures, privacy-preserving techniques, healthcare applications, deployment challenges, and future research directions.
- Venue: ACM Computing Surveys
Journal
In Progress
Comparison of 7 Generic Federated Learning Frameworks on Kidney Graft Survival with Implementation
This comparative experimental study evaluates seven federated learning frameworks—including Flower, FedML, and PySyft—using the OPTN kidney transplant dataset, comparing performance, scalability, communication efficiency, and privacy.
- Venue: Research Study
Whitepaper
Published · Published · 2026
Building a Digital Culture That Makes Tech Projects Work
A qualitative guide for industry, based on original interviews with 80+ UK companies.
Practical insight for business leaders preparing to invest in digital tools and AI, with a focus on the culture, leadership and adoption behaviours that make technology projects succeed.
Practical insight for business leaders preparing to invest in digital tools and AI, with a focus on the culture, leadership and adoption behaviours that make technology projects succeed.
- Based on interviews with 80+ UK companies employing between 10 and 10,000 people.
Whitepaper
Published · Published · 2026
Bridging the Digital Delivery Gap in Manufacturing
A qualitative guide for manufacturers under pressure to improve margins, lead times and operational reliability.
Based on original interviews with 80+ UK companies, this guide explores the common barriers stopping manufacturers from turning digital investment into measurable delivery improvements.
Based on original interviews with 80+ UK companies, this guide explores the common barriers stopping manufacturers from turning digital investment into measurable delivery improvements.
- Created for manufacturing leaders looking for practical, lower-risk entry points into digital improvement, AI and automation.
In Progress · Submitted (30 June 2026)
FGNN-DT: A Privacy-Preserving Federated Graph Learning and Digital Twin Framework for Breast Cancer Recurrence Prediction
The paper integrates federated graph learning with digital twin technology for breast cancer recurrence prediction. The framework combines privacy preservation, graph neural networks, and digital twins for clinically informed prediction.
- Venue: IEEE Journal of Biomedical and Health Informatics (J-BHI) Special Issue: 'Federated Learning and Digital Twins for Smart Healthcare'
In Progress · Submitted
Federated Graph Learning for Resilient Healthcare Infrastructure Modelling in OPTN Transplant Network
This work models OPTN transplant networks using federated graph learning to improve resilience and knowledge sharing across distributed healthcare infrastructures while preserving data privacy.
- Venue: ICA2S 2026