Jin Chen, Ph.D., vice chair for Education in the Department of Biomedical Informatics and Data Sciences, has been awarded the Priya Nagar, M.D., Innovation Award for Kidney-Related Diseases. The award is a collaboration with Javier Neyra, M.D., associate professor in the Division of Nephrology, who is co-leading the project. Tiago Colicchio, Ph.D., assistant professor in the Department of Biomedical Informatics and Data Science, is also a collaborator on the project. The team is working with Dialytix, LLC—a UAB start-up led by CEO Ruben Raposo.

The Priya Nagar, M.D., Innovation Award supports innovative, high-impact, and cutting-edge research that will result in new intellectual property, commercial partnerships, or ideas that lead to a patent.

Priya Nagar, M.D., was a dedicated physician in Montgomery Alabama and a kidney transplant recipient. In 2017, at the age of 36, Priya lost her battle with a rare form of lymphoma, a complication of long-term immunotherapy for her CKD and previous kidney transplant. This award is a tribute to her research and belief that future research would help better treat kidney disease. Her family honors her legacy with these awards to accelerate research efforts into understanding kidney disease better at UAB. Read more about her moving story.

The project’s work focuses on “developing SMART-CRRT, an artificial intelligence (AI)-powered clinical decision support tool designed to help health care professionals optimize treatment decisions for critically ill patients with acute kidney injury (AKI) undergoing continuous renal replacement therapy (CRRT),” Chen says.

“The system integrates data from electronic health records (EHR) and CRRT machines, addressing the challenge of fragmented and unstructured clinical data.”

Chen explains that by analyzing these diverse data sources in real time, SMART-CRRT provides personalized treatment recommendations, enhances clinical workflows, improves patient outcomes, and ensures timely and precise interventions—solutions to fragmented processes that will ultimately help patients achieve greater outcomes.

The Department of Biomedical Informatics and Data Science communications team sat down with Chen and Colicchio to learn more about the clinical informatics project and its impact on kidney disease.

How will the Priya Nagar, M.D., Innovation Award impact the future of your work?

Chen: This award will provide critical preliminary data necessary to secure additional funding, supporting the development, validation, and real-world integration of SMART-CRRT at UAB. It also focuses on advancing AI-driven predictive models for CRRT management and supporting clinical adoption.

How does this work contribute to kidney disease?

Chen: SMART-CRRT directly addresses two key clinical challenges in nephrology: when to start CRRT and when to safely stop it. Currently, these decisions are largely based on clinical experience rather than evidence-driven insights. By leveraging AI models trained on multimodal patient data, SMART-CRRT aims to identify clinical markers of CRRT, improve decision-making, enhance patient safety, and ensure more effective resource utilization.

Could you speak to why this work is important regionally?

Chen: In the Deep South, where the kidney disease rate is disproportionately high, healthcare disparities—including limited access to nephrology specialists and advanced medical technologies—contribute to suboptimal AKI care. SMART-CRRT is designed to support local hospitals, ensuring more consistent and efficient CRRT management. This system has the potential to help reduce variability in care and support improved patient outcomes, particularly in resource-limited settings.

What are the long-term implications of the project?

Chen and Colicchio: The long-term goal of SMART-CRRT is to advance clinical decision support (CDS) in nephrology by improving how patient data is integrated, processed, and utilized in real time. While initially focused on optimizing CRRT management for AKI patients, this approach has broader implications for critical care medicine. This study will build the foundation for a standards-based platform to facilitate shared CDS functionality using widely adopted CDS standards based on Fast Healthcare Interoperability Resources (FHIR). By refining AI-assisted data harmonization and predictive modeling delivered using CDS standards, the methodologies developed for SMART-CRRT could be extended to other acute conditions, such as sepsis management and hemodynamic monitoring in intensive care units.