What happened
Renalytix AI makes KidneyIntelX.dkd, a test for adults with type 2 diabetes and early chronic kidney disease. It combines three blood biomarkers with urine albumin, HbA1c and BUN from the patient's records, using a random forest model built with machine learning. Renalytix validated it retrospectively on biobanked samples from 657 adults, collected at 10 clinical sites. FDA reviewers report estimated five-year rates of a sustained fall of 40% or more in kidney function of 5.9%, 21.5% and 66.9% in the low, moderate and high levels. The differences held after adjustment for age, sex, race, blood pressure and baseline kidney measures. FDA granted the De Novo request on 29 June 2023. FDA notes that the test may help decide which patients need more monitoring or treatment. The samples were archived, so the levels guided no care.
Sources
-
Regulatory document, by authors with no tie to the system.
U.S. Food and Drug Administration, Center for Devices and Radiological Health. Evaluation of automatic class III designation for KidneyIntelX.dkd (DEN200052): decision summary. Granted 2023-06-29.
The test provides additional independent patient-specific prognostic information on the risk profile of patient with DKD that can be used by physician/healthcare providers to inform management decisions for individual patients.
Details
AI system
- Workflow
-
TNFR-1, TNFR-2 and KIM-1 were measured in plasma at the Renalytix laboratory. Clinicians supplied urine albumin, HbA1c and BUN from the previous 12 months.
Follow-up
- Conditions for replication
-
The patient is an adult with type 2 diabetes and chronic kidney disease as the labeling defines it. Results are read with other clinical findings and never alone.
Entry details
- Sector
-
Healthcare.
- Purpose
-
Renalytix built KidneyIntelX.dkd to help clinicians assess the five-year risk of progressive decline in kidney function in adults with type 2 diabetes and existing kidney disease.
Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). KidneyIntelX.dkd sorted diabetic kidney patients by risk of decline (AIBD-0776). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0776.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)