Derivation and independent validation of kidneyintelX .dkd: A prognostic test for the assessment of diabetic kidney disease progression
Authors' conclusion
Using two independent cohorts and a clinical trial population, we validated an updated KidneyIntelX test (named kidneyintelX.dkd), which significantly enhanced risk stratification in patients with DKD for PDKF, independently from known risk factors for progression.
Study context
- Population
- Patients with diabetic kidney disease (DKD) stages 1 to 3; training in Penn Medicine Biobank (PMBB), validation in BioMe and CANVAS cohorts573 PMBB, 657 BioMe, 1197 CANVAS
- Comparison
- High- and moderate- vs low-risk kidneyintelX.dkd levels
- Outcome
- Progressive decline in kidney function (PDKF): ≥40% sustained decline in eGFR or end-stage kidney disease
- Follow-up
- Within 5 years
Methodological detailsrandom forest model, independent external validation cohorts
- Random forest model
- Independent external validation cohorts
Performance
As reported in the abstract
PDKF by risk level, adjusted for clinical risk factors
Low-risk
5.9% (BioMe); 6.7% (CANVAS)
Moderate-risk
21.2% (BioMe); 13.1% (CANVAS)
High-risk
66.9% (BioMe); 59.6% (CANVAS)
Each group vs low-riskAdjusted hazard ratio (95% CI)
High-riskBioMe
7.7(3.0–19.6)
Moderate-riskBioMe
3.7(2.0–6.8)
High-riskCANVAS
5.4(2.5–11.9)
Moderate-riskCANVAS
2.3(1.4–3.9)
Further findings
Progressive decline in kidney function (PDKF) incidence by cohort
- PMBB (training), over median 3.7 years
- 15.4%
- BioMe
- 11.7%
- CANVAS
- 7.5%
Original publication
Derivation and independent validation of kidneyintelX .dkd: A prognostic test for the assessment of diabetic kidney disease progression. Diabetes Obes Metab. Published 18 September 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →