MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641108172 A) filed by Pragati Engineering College on September 09, 2026, for Context-Adaptive Reliability-Aware Multi-Modal Data Fusion With Explainable Ai For Clinical Decision Support.
Inventors include Mr. M. V. Rajesh; Mr. Srikanth Kosaraju; Mr. K. V. S. Akhil; and Mrs. G. Viranya.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: The invention provides an intelligent framework for integrating heterogeneous healthcare data, including medical images, physiological signals, laboratory reports, Electronic Health Records (EHRs), wearable device data, and clinical notes, to support accurate and transparent clinical decision-making. Initially, multi-modal patient data are acquired, preprocessed, standardized, and transformed into a unified feature representation. A context identification engine determines the patient's clinical condition, while a reliability assessment engine evaluates the quality, completeness, and consistency of each data modality to assign reliability scores. A context- adaptive multi-modal data fusion engine dynamically combines the extracted features by considering both clinical context and modality reliability, generating a comprehensive patient representation. An Explainable Artificial Intelligence (XAI)-based clinical prediction engine analyzes the fused data to perform disease diagnosis, risk assessment, severity estimation, and outcome prediction while providing interpretable explanations, confidence scores, and feature importance rankings. An intelligent clinical decision support system generates personalized diagnostic recommendations, treatment suggestions, clinical alerts, and patient prioritization to assist healthcare professionals in informed decision-making. Furthermore, an adaptive learning and knowledge refinement engine continuously updates the framework using clinician feedback, patient outcomes, and newly acquired healthcare data, thereby improving prediction accuracy and system reliability over time. The proposed invention overcomes the limitations of conventional clinical decision support systems by introducing context-aware processing, reliability-driven data fusion, and explainable AI, resulting in enhanced diagnostic accuracy, transparency, robustness, and trustworthiness across diverse healthcare applications.
Disclaimer: Curated by HT Syndication.
