Using AI to predict outcomes for people on continuous dialysis for acute kidney injury
Official title: Artificial Intelligence to Predict Outcomes in Patients with Acute Kidney Injury on Continuous Renal Replacement Therapy
Funded at University of Alabama at Birmingham · NIH-11309119 · Data updated 2026-11-12
This project uses artificial intelligence to predict survival and whether kidneys will recover for ICU patients receiving continuous dialysis for acute kidney injury.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Alabama at Birmingham NIH-funded |
| Lab location | 1 site (Birmingham, United States) |
| Project start | April 1, 2023 |
| Project end | January 31, 2027 |
| Funding year | 2026 |
| Award (this year) | $666,128 |
| NIH project number | 5R01DK133539-04 |
| Project ID | NIH-11309119 on NIH RePORTER |
Who could benefit from this research
✓Could help
The ideal candidates are adult ICU patients with acute kidney injury who are receiving continuous renal replacement therapy (continuous dialysis).
✕Less likely to help
People not in the ICU, those not receiving continuous dialysis, and patients on chronic maintenance dialysis are unlikely to directly benefit from this project.
What this research studies
If you are in the ICU with acute kidney injury and need continuous renal replacement therapy (continuous dialysis), researchers will use your routine health data to train deep learning models that predict survival and dialysis-free recovery. They will combine lab results, monitor data, treatments, and other clinical information to build and test these models. The team will also apply a Feasible Solution Algorithm to identify subgroups of patients who have different risks and might benefit from different care approaches. Models will be validated on separate patient datasets to check that predictions are accurate and reproducible.
Why it matters
Potential benefit: If successful, this could give doctors better, personalized information about likely survival and kidney recovery to guide dialysis decisions and post-ICU care.
How similar studies have gone: Some prior machine-learning work has predicted acute kidney injury outcomes, but accurate, widely accepted tools specifically for patients on continuous renal replacement therapy are limited, so this approach builds on prior AI work but remains relatively novel for this subgroup.
Where this research is happening
-
University of Alabama at Birmingham
Birmingham, United States Active
Researchers
- Principal investigator: Neyra, Javier a. — University of Alabama at Birmingham
- Study coordinator: Neyra, Javier a.
Related research
Other NIH-funded projects on the same topics.
-
SEAK Alliance: Improving Care for AKI Patients in the Southeast
A national, patient-centered effort to improve post-hospital care for people who had acute kidney injury in the Southeast.
-
AKI-related delirium after heart surgery
This grant funds research to understand why some people develop delirium after heart surgery when they also have acute kidney injury.
-
Better ways to identify types of sudden kidney injury in U.S. Veterans
Researchers are looking for genetic and health patterns that define different types of sudden severe kidney injury in Veterans to help guide future care.
-
Neuroimmune control of kidney injury using noninvasive ultrasound
A new approach uses targeted ultrasound to gently stimulate nerves and immune signals to help the kidney recover after injury.
-
Structure-based approach to prevent kidney injury from polymyxin use
Aims to block how polymyxin damages the kidney so it can be used more safely to treat hard-to-kill infections.
-
Using smart computer predictions to prevent kidney injury after heart surgery
A machine-learning approach uses routinely collected hospital data to predict who might develop acute kidney injury after heart surgery, so clinicians can act early.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.