Abstract: TH-PO631
Peripheral Blood Cell DNA Methylation Can Predict Steroid Response in Nephrotic Syndrome
Session Information
- Membranous Nephropathy, FSGS, and Minimal Change Disease
October 24, 2024 | Location: Exhibit Hall, Convention Center
Abstract Time: 10:00 AM - 12:00 PM
Category: Glomerular Diseases
- 1402 Glomerular Diseases: Clinical, Outcomes, and Therapeutics
Authors
- Hayward, Samantha JL, University of Bristol, Bristol, United Kingdom
- Suderman, Matthew, University of Bristol, Bristol, United Kingdom
- Welsh, Gavin Iain, University of Bristol, Bristol, United Kingdom
- Saleem, Moin A., University of Bristol, Bristol, United Kingdom
Background
The majority of children with idiopathic nephrotic syndrome (INS) and adults with Focal Segmental Glomerulosclerosis (FSGS) and Minimal Change Disease (MCD) receive glucocorticoid treatment at diagnosis. Overall, about 10% will not respond to steroid treatment and we have no reliable way of prospectively identifying these patients. DNA methylation (DNAm) is an epigenetic mechanism meaning that it can induce stable but reversible changes in gene expression without any change in underlying DNA sequence. DNAm has shown great potential as a treatment stratification tool in other disease settings.
We investigated whether DNAm can predict initial response to steroids in children and young adults with INS.
Methods
Two hundred and eighty one INS patients recruited to the NephroS and NURTuRE cohorts were selected. All patients had been diagnosed with INS ≤ 30 years of age and those who underwent a renal biopsy had a histological diagnosis of FSGS or MCD. Peripheral blood DNAm measurements were generated using the Illumina MethylationEPIC Beadchip (>850,000 CpG sites). Clinical data was used to label patients by their initial response to steroids.
Machine learning models were created to predict steroid response from the DNAm data. Models were generated using elastic net following feature filtering, and model hyperparameters were tuned and performance measured within the context of cross validation.
Results
The 281 INS patients had a median age at diagnosis of 5 years (IQR 2-10) and the majority were white (n=198, 71%). The median time between diagnosis and DNAm sample collection was 4 years (IQR 1-10). One hundred and thirty five patients were sensitive to their first course of steroids and 146 were resistant. The steroid resistant group included patients with known monogenic disease (n=46, 31%).
Using the DNAm data, initial response to steroid treatment could be predicted with 70% accuracy and an area under the curve (AUC) of 0.76, (sensitivity 0.79, specificity of 0.60, Figure 1). The final steroid response prediction model contained 14 CpG sites.
Conclusion
We have demonstrated that peripheral blood cell DNAm profiles are a promising predictor of steroid response in INS. Further work to incorporate genetic data into the prediction models is underway and external validation of the results in a separate cohort of patients is required.