MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641061609 A) filed by Nri Institute Of Technology; Ms. Lavanya Gumpena; Mr. Muni Murari Krishna Koravi; Ms. Bhavani Sivala; Mr. Lakshman Sai Satyam Pallapothu; Mrs. S. Rama Devi; and Dr. Sivaramakrishna Yechuri, Eluru, Andhra Pradesh, on May 14, for 'an interpretable lightgbm-smote framework for early prediction of chronic kidney disease.'
Inventor(s) include Ms. Lavanya Gumpena; Mr. Muni Murari Krishna Koravi; Ms. Bhavani Sivala; Mr. Lakshman Sai Satyam Pallapothu; Mrs. S. Rama Devi; and Dr. Sivaramakrishna Yechuri.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "Early diagnosis of chronic kidney disease (CKD) is critical to avoid the progression of the disease and alleviate the healthcare system. However, the CKD datasets often suffer from class imbalance, limited robustness, and a lack of interpretability. In this paper, an interpretable machine learning framework combining Light Gradient Boosting Machine (LightGBM) and Synthetic Minority Oversampling Technique (SMOTE) is proposed to counter class imbalance issues while preserving high accuracy. The hyperparameters are tuned using RandomizedSearchCV with a stratified 5-fold cross-validation strategy to prevent overfitting and ensure generalization. Accuracy, Precision, Recall, F1-score, and ROC-AUC are used to measure the performance of the proposed framework. Moreover, SHapley Additive exPlanations (SHAP) is utilized to inject feature-level interpretability and improve clinical credibility. The experimental outcome shows that the proposed framework achieves a mean accuracy of 98.25% and a ROC-AUC of 99.93%, indicating strong discriminative capability. The proposed framework is a trustworthy and interpretable solution for early CKD diagnosis and medical decision support."
Disclaimer: Curated by HT Syndication.
