Javier Neyra, M.D.Javier Neyra, M.D., M.S.C.S., associate professor in the Department of Medicine, Division of Nephrology received a $3.8 million R01 grant from the National Institute of Diabetes and Digestive and Kidney Diseases at the NIH for his project "Artificial Intelligence to Predict Outcomes in Patients with Acute Kidney Injury on Continuous Renal Replacement Therapy (CRRT)."
Neyra is the co-director of the Critical Care Nephrology program at UAB, co-director of the Clinical Core of the UAB-UCSD O'Brien Center for Acute Kidney Injury Research, and the associate director of the Nephrology Research & Training Center. His areas of expertise include critical care nephrology, acute kidney injury, and renal replacement therapies.
"This is a multicenter project that will assist with the development and validation of digital health tools for risk-classification and sub-phenotyping of critically ill adult patients receiving CRRT,” said Neyra. “These tools could augment bedside decisions by clinicians, as well as facilitate quality control and assurance in the delivery of CRRT, which is the second most common extracorporeal support device in the Intensive Care Unit (ICU).”
Acute kidney injury affects up to half of the critically ill patients admitted to ICUs. CRRT therapy is the preferred dialysis treatment for these patients, but the mortality rate is high. Currently, there are no accurate approaches for predicting survival or kidney recovery in these patients.
Due to advances in artificial intelligence (AI) and the availability of multi-modal data, deep learning –a subset of AI– allows the construction of accurate and reliable risk prediction models. Furthermore, the use of novel algorithms such as the Feasible Solution Algorithm (FSA) could help identify patient sub-phenotypes and model applications.
Neyra’s project proposes to deliver innovative deep-learning approaches to predict dialysis-free survival at actionable time points and use FSA to identify patient sub-phenotypes for model interpretation and clinical utility testing.
This innovative research will assist the development of clinical decision support platforms to guide informed CRRT delivery, improve clinical outcomes and identify sub-phenotypes of patients that could benefit from more personalized and testable novel CRRT interventions.
Neyra acknowledges his co-investigators, Lili Chan, M.D. (Icahn School of Medicine at Mount Sinai), Jin Chen, Ph.D. (University of Kentucky), Stuart Goldstein, M.D. (Cincinnati Children’s), Sara Hendrix, Ph.D. (University of Alabama), Josh Lambert, Ph.D. (University of Cincinnati) and Girish Nadkarni, M.D. (MPI of the project) for their invaluable contributions.