EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Radiomics Nomogram for Early Diabetic Kidney Injury Prediction from Ultrasound Cohorts

Chiara Ferrara, Greta Becker, Marcus Douglas

International Journal of Computational and Biological Sciences · 25.06.2026 · 3 (2) · 97-111

DOI: 10.66238/ijcbs89 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computational and Biological Sciences, online erschienen am 25.06.2026. Verfasst von Chiara Ferrara und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic kidney disease represents a major microvascular complication of diabetes mellitus and is a leading cause of end-stage renal disease globally. Early identification of renal injury is paramount for implementing interventions that can halt or reverse disease progression. However, traditional biomarkers such as microalbuminuria and estimated glomerular filtration rate often lack the sensitivity required to detect the earliest structural and functional alterations in the kidneys, particularly in resource-constrained community settings. This study investigates the development and validation of a radiomics-based clinical nomogram utilizing routine renal ultrasound imaging combined with standard clinical data to predict early diabetic kidney injury in a community cohort. We present a comprehensive methodology encompassing cohort selection, standardized ultrasound image acquisition, high-throughput radiomics feature extraction, and dimensionality reduction. Using a multivariable logistic regression framework, we construct a predictive nomogram that integrates a robust radiomics signature with key clinical determinants, including glycated hemoglobin levels and duration of diabetes. Our analysis demonstrates that the combined radiomics-clinical nomogram significantly outperforms clinical-only models in terms of discrimination and calibration. Furthermore, decision curve analysis confirms the clinical utility of the nomogram across a wide range of threshold probabilities, highlighting its potential as a non-invasive, cost-effective screening tool. By leveraging ubiquitous ultrasound technology and advanced image analysis, this predictive model offers a pragmatic approach for risk stratification and early intervention in community-based diabetic populations, thereby addressing a critical gap in primary care diagnostics.

Zitieren

APA

Ferrara, C., Becker, G., & Douglas, M. (2026). Radiomics Nomogram for Early Diabetic Kidney Injury Prediction from Ultrasound Cohorts. International Journal of Computational and Biological Sciences, 3(2), 97-111. https://doi.org/10.66238/ijcbs89

Vancouver

Ferrara C, Becker G, Douglas M. Radiomics Nomogram for Early Diabetic Kidney Injury Prediction from Ultrasound Cohorts. International Journal of Computational and Biological Sciences. 2026;3(2):97-111. doi:10.66238/ijcbs89

BibTeX
@article{Ferrara2026,
  author = {Ferrara, Chiara and Becker, Greta and Douglas, Marcus},
  title = {Radiomics Nomogram for Early Diabetic Kidney Injury Prediction from Ultrasound Cohorts},
  journal = {International Journal of Computational and Biological Sciences},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {97--111},
  doi = {10.66238/ijcbs89}
}
Kostenlos starten →