KAUST Ph.D. student Michał Mańkowski's research on kidney allocation strategies was recognized as one of the American Journal of Transplantation's "Top 10 Articles of 2019." The research demonstrated how an accelerated allocation strategy could increase the utilization of kidneys at risk for non-use, potentially reducing discard rates. Mańkowski aims to translate his U.S.-focused research to improve organ transplantation within the Saudi Arabian healthcare system. Why it matters: This research has the potential to improve organ transplant outcomes and resource allocation in Saudi Arabia, addressing a critical healthcare need.
KAUST Ph.D. student Michał Mańkowski won a Poster of Distinction Award at the American Society of Transplant Surgeons (ASTS) 18th Annual State of the Art Winter Symposium for his work on kidney allocation systems. His poster described a simulation for a new kidney allocation system to accelerate organ placement, focusing on marginal quality kidneys. The research involves combinatorial optimization, operation research and management science with healthcare applications, stemming from a collaboration with Johns Hopkins School of Medicine. Why it matters: The research aims to improve organ transplantation efficiency and save lives by optimizing kidney allocation systems, demonstrating the potential of AI and optimization techniques in healthcare.
This paper introduces an explainable machine learning framework for early-stage chronic kidney disease (CKD) screening, specifically designed for low-resource settings in Bangladesh and South Asia. The framework utilizes a community-based dataset from Bangladesh and evaluates multiple ML classifiers with feature selection techniques. Results show that the ML models achieve high accuracy and sensitivity, outperforming existing screening tools and demonstrating strong generalizability across independent datasets from India, the UAE, and Bangladesh.
A KAUST team designed an enhanced transfer system for Saudi Arabia's Ministry of Health (MOH) to address employee localization challenges. The system aims to improve staff distribution across the Kingdom and increase employee satisfaction by offering transparency and optimized HR allocation. The team, led by Omar Knio, Sultan Al-Barakati, and Ricardo Lima, developed dashboards for real-time application tracking and individual scoring. Why it matters: The collaboration between KAUST and MOH demonstrates the potential of AI and optimization to address critical human resource challenges in the public sector and improve healthcare services in Saudi Arabia.
This paper introduces MOTOR, a multimodal retrieval and re-ranking approach for medical visual question answering (MedVQA) that uses grounded captions and optimal transport to capture relationships between queries and retrieved context, leveraging both textual and visual information. MOTOR identifies clinically relevant contexts to augment VLM input, achieving higher accuracy on MedVQA datasets. Empirical analysis shows MOTOR outperforms state-of-the-art methods by an average of 6.45%.
This paper introduces DaringFed, a novel dynamic Bayesian persuasion pricing mechanism for online federated learning (OFL) that addresses the challenge of two-sided incomplete information (TII) regarding resources. It formulates the interaction between the server and clients as a dynamic signaling and pricing allocation problem within a Bayesian persuasion game, demonstrating the existence of a unique Bayesian persuasion Nash equilibrium. Evaluations on real and synthetic datasets demonstrate that DaringFed optimizes accuracy and convergence speed and improves the server's utility.