Integrating DenseNet and Ensemble Learning for Multimodal Prediction of Chronic Kidney Disease Stages
International Journal of Research in Advent Technology · 30.06.2026 · 1-6
DOI: 10.32622/ijrat.1402202603 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Research in Advent Technology, online erschienen am 30.06.2026. Verfasst von Utkarsha Rane und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Chronic Kidney Disease (CKD) is a major global health concern, and early detection is critical to preventing disease progression and associated complications.Conventional CKD diagnosis based on ultrasound image interpretation often suffers from interobserver variability and limited diagnostic consistency.Moreover, many existing artificial intelligence-based studies rely on single-modality data, which restricts predictive performance and limits clinical applicability.To address these limitations, this study proposes a multimodal deep learning framework that integrates ultrasound imaging data with clinical tabular information for accurate CKD stage prediction.The proposed approach employs a DenseNet-based convolutional neural network to extract discriminative features from ultrasound images, while ensemble learning techniques are used to improve classification robustness and predictive accuracy.The model was evaluated using a dataset of 3,734 samples categorized into four classes: Normal, Cyst, Stone, and Tumor.Experimental results demonstrate strong predictive performance, achieving an overall accuracy of 99%, with precision, recall, and F1-score values of 0.99 across all classes.These findings indicate that the proposed multimodal framework significantly enhances diagnostic reliability and has strong potential to support clinicians in early CKD detection and improved decision-making in clinical practice.
Zitieren
APA
Rane, U., & Kolhe, D. S. R. (2026). Integrating DenseNet and Ensemble Learning for Multimodal Prediction of Chronic Kidney Disease Stages. International Journal of Research in Advent Technology, 1-6. https://doi.org/10.32622/ijrat.1402202603
Vancouver
Rane U, Kolhe DSR. Integrating DenseNet and Ensemble Learning for Multimodal Prediction of Chronic Kidney Disease Stages. International Journal of Research in Advent Technology. 2026:1-6. doi:10.32622/ijrat.1402202603
BibTeX
@article{Rane2026,
author = {Rane, Utkarsha and Kolhe, Dr. Satish Ramesh},
title = {Integrating DenseNet and Ensemble Learning for Multimodal Prediction of Chronic Kidney Disease Stages},
journal = {International Journal of Research in Advent Technology},
year = {2026},
pages = {1--6},
doi = {10.32622/ijrat.1402202603}
}
EUVIMED