MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641049897 A) filed by Easwari Engineering College; and Srm Institute Of Science And Technology, Ramapuram Campus, Chennai, Tamil Nadu, on April 20, for 'inceptionv3 and xgboost fusion for early prediction of chemotherapy induced cardiotoxicity in breast cancer patients.'
Inventor(s) include Megala P; Rithanya V R; and Preethi B.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The present invention provides a multimodal artificial intelligence system for predicting chemotherapy-induced cardiotoxicity in breast cancer patients by integrating cardiac imaging data with structured clinical variables. A pretrained InceptionV3 convolutional neural network analyses Tissue Doppler Imaging echocardiography frames to extract spatial cardiac features indicative of early myocardial dysfunction, capturing subtle motion abnormalities not easily detected through conventional evaluation. In parallel, an XGBoost gradient boosting model processes clinical variables including demographics, baseline cardiac metrics, comorbidities, and treatment-related factors to identify nonlinear relationships associated with cardiotoxicity risk. Outputs from both models are combined through a decision-level fusion mechanism to generate a final risk prediction. The system provides interpretable results categorized as "At Risk" or "Not At Risk" with an associated confidence score. Utilizing routinely available data and a lightweight architecture, the invention enables early risk detection, supports timely clinical decision-making, improves patient outcomes, and enhances overall treatment monitoring efficiency."
Disclaimer: Curated by HT Syndication.
