Predicting kidney disease worsening in adults with sickle cell anemia
Official title: Predicting Progression of Chronic Kidney Disease in Sickle Cell Anemia Using Machine Learning Models (PREMIER)
Funded at University of Tennessee Health Sci Ctr · NIH-11161553 · Data updated 2026-11-12
Using computer learning to spot which adults with sickle cell anemia are most likely to have their kidney disease get worse.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Tennessee Health Sci Ctr NIH-funded |
| Lab location | 1 site (Memphis, United States) |
| Project start | September 10, 2021 |
| Project end | August 31, 2026 |
| Funding year | 2025 |
| Award (this year) | $610,088 |
| NIH project number | 5R01HL159376-05 |
| Project ID | NIH-11161553 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults (21+) with sickle cell anemia, especially individuals of African descent who have albuminuria or declining kidney function, are the ideal participants.
✕Less likely to help
People without sickle cell disease, children under 21, or those without available clinical or genetic data are unlikely to be eligible or to benefit directly.
What this research studies
If you join, researchers will use your medical records, blood and urine tests, and genetic results to train computer models that try to predict who will have faster kidney decline. The team looks at measurements such as albumin in the urine, eGFR trends, hemoglobin levels, APOL1 genetic variants, and medications like ACE inhibitors, ARBs, or hydroxyurea. Models will be developed and tested to flag patients at high risk of rapid kidney function loss. The goal is to identify people who may need closer monitoring or targeted care to slow progression.
Why it matters
Potential benefit: Could help doctors identify high-risk patients earlier so they can receive closer monitoring or treatments that might slow kidney damage.
How similar studies have gone: Short-term studies show ACE inhibitors, ARBs, and hydroxyurea can reduce albuminuria and prior machine-learning work has shown promise in flagging high-risk patients, but long-term prevention of kidney decline in sickle cell disease remains unproven.
Where this research is happening
-
University of Tennessee Health Sci Ctr
Memphis, United States Active
Researchers
- Principal investigator: Ataga, Kenneth I — University of Tennessee Health Sci Ctr
- Study coordinator: Ataga, Kenneth I
Related research
Other NIH-funded projects on the same topics.
-
Using machine learning to predict kidney disease progression in sickle cell anemia
This study is looking at how computer models can help predict kidney problems in people with sickle cell anemia by checking things like protein levels in urine and genetic information, so we can find those who might need extra care early on to keep their kidneys healthy.
-
Personalized CKD-MBD care using systems biology and AI
A patient-facing program aims to tailor mineral-balance therapy for people with chronic kidney disease by using a computer model and smart decision rules to predict who will respond best to treatments.
-
Hydroxyurea to help children with sickle cell anemia in Africa
A pediatric study tests hydroxyurea treatment for young children with sickle cell anemia in several African countries to see if it can reduce illness and improve health.
-
Hydroxyurea for Children with Sickle Cell in Africa
A pilot study tests hydroxyurea in young children with sickle cell disease across several African countries to see if it can reduce illness and hospital visits.
-
Hydroxyurea for Children with Sickle Cell Disease in Africa
A safe and feasible use of hydroxyurea for young children with sickle cell disease in several African countries to reduce illness and improve daily life.
-
Mitigating DKA in people with type 1 diabetes and kidney disease using SGLT1/2 inhibitors
This project tests a new way to prevent dangerous diabetic ketoacidosis in people with type 1 diabetes and chronic kidney disease who are using SGLT inhibitors, by tracking ketones in real time and combining glucose-keton data for safer therapy.
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.