In silico prediction of optimal multifactorial intervention in chronic kidney disease
Authors:
Open Access
- 21 August 2025
- journal article
- research article
- Published by Springer Nature in Journal of Translational Medicine
- Vol. 23 (1) , 1-10
Abstract
Background: Chronic kidney disease (CKD) contributes to global morbidity and mortality. Early, targeted intervention can help mitigate its impact. CK273 is a urinary peptide classifier previously validated in a prospective clinical trial for the early detection of nephropathy. We hypothesized that drug-induced molecular changes in the urinary peptidome could be predicted in silico and guide selecting interventions for individual patients. Methods: The efficacy of the urinary peptidomic classifier CKD273 in predicting major adverse kidney events (≥ 40% decline in estimated glomerular filtration rate or kidney failure -median follow-up: 1.50 (95%CI 0.35, 5.0) years), was confirmed in a retrospective cohort of 935 participants. In silico prediction of treatment effects from four drug-based interventions (Mineralocorticoid receptor antagonist, Sodium-glucose co-transporter 2 inhibitor, Glucagon-like peptide-1 receptor agonist, and Angiotensin receptor blocker), dietary intervention (olive oil), and exercise was performed based on: a) individual baseline urinary peptide profiles, and b) previously defined fold changes in peptide abundance after treatment in clinical trials. Following recalibration to align with outcomes of these trials, CKD273 scores were calculated for each patient after in silico treatment. For combination treatments, the effects of multiple interventions were combined. Results: Simulated interventions demonstrated a significant reduction in median CKD273 scores, from 0.57 (IQR: 0.19–0.81) before to 0.039 (IQR: −0.192–0.363) after the most beneficial intervention (paired Wilcoxon test, P < 0.0001). The combination of all available treatments was not the most frequently predicted optimal intervention. Patients with higher baseline CKD273 scores required more complex intervention combinations to achieve the greatest score reduction. Conclusions: This study supports the feasibility of in silico predicting effects of therapeutic interventions on CKD progression. By identifying the most beneficial treatment combinations for individual patients, this approach paves the way for precision medicine trials in CKD. A prospective study is currently being planned to validate the in silico-guided intervention approach and determine its exact benefits on patient-relevant outcomes.Keywords
Funding Information
- Bundesministerium für Forschung, Technologie und Raumfahrt (01EK2105A, 01EK2105B, 01EK2105C, 01KU2307)
- Austrian Science Fund (I 6464, Grant-DOI 10.55776/I6464)
- Agence Nationale de la Recherche (ANR-22-PERM-0002-06)
- Bundesministerium für Wirtschaft und Klimaschutz (ZIMKK5560002AP3)
- Horizon 2020 Framework Programme (848011)
- HORIZON EUROPE Marie Sklodowska-Curie Actions (101072828, 101168626)
- HORIZON EUROPE Marie Sklodowska- Curie Actions (101072828)
- European Cooperation in Science and Technology (CA21165)
- European Health and Digital Executive Agency (101101220)
- FIS/Fondos FEDER (AC22/00027)
- Comunidad de Madrid en Biomedicina (P2022/BMD-7223, CIFRACOR-CM)
- Instituto de Salud Carlos III (RICORS program to RICORS2040 (RD21/0005/0001), SPACKDc PMP21/00109)
This publication has 41 references indexed in Scilit:
- Prediction Modeling With Many Correlated and Zero‐Inflated Predictors: Assessing the Nonnegative Garrote ApproachStatistics in Medicine, 2025
- Predictive performance and clinical application of COV50, a urinary proteomic biomarker in early COVID-19 infection: a prospective multicentre cohort studyThe Lancet Digital Health, 2022
- Renal Protection with SGLT2 Inhibitors: Effects in Acute and Chronic Kidney DiseaseCurrent Diabetes Reports, 2022
- Early detection of diabetic kidney disease by urinary proteomics and subsequent intervention with spironolactone to delay progression (PRIORITY): a prospective observational study and embedded randomised placebo-controlled trialThe Lancet Diabetes & Endocrinology, 2020
- Review of precision cancer medicine: Evolution of the treatment paradigmCancer Treatment Reviews, 2020
- Forecasting life expectancy, years of life lost, and all-cause and cause-specific mortality for 250 causes of death: reference and alternative scenarios for 2016–40 for 195 countries and territoriesThe Lancet, 2018
- Proteomics for prediction of disease progression and response to therapy in diabetic kidney diseaseDiabetologia, 2016
- Practical Approach to Detection and Management of Chronic Kidney Disease for the Primary Care ClinicianThe American Journal of Medicine, 2016
- Technical aspects and inter-laboratory variability in native peptide profiling: The CE–MS experienceClinical Biochemistry, 2013
- Quantitative Urinary Proteome Analysis for Biomarker Evaluation in Chronic Kidney DiseaseJournal of Proteome Research, 2008