MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641049566 A) filed by Sr University, Warangal, Telangana, on April 18, for 'integrate explainability techniques to improve clinical interpretability and trust in ai-driven diagnostics.'

Inventor(s) include Sriramula Naveena; and Dr. Kummari Venkatesh.

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 relates to an explainable artificial intelligence-based diagnostic system designed to enhance transparency, interpretability, and trust in clinical decision-making processes. The system integrates multimodal healthcare data, including medical imaging, physiological signals such as ECG, laboratory results, and electronic health records, to generate accurate and context-aware diagnostic predictions. Unlike conventional black-box machine learning models, the proposed system incorporates advanced explainability techniques that provide clear and clinically meaningful insights into how predictions are generated. These techniques include feature attribution methods, attention-based mechanisms, and model-agnostic interpretability approaches that collectively identify and highlight the most influential factors contributing to diagnostic outcomes. The system is capable of generating real-time explanations alongside predictive outputs, enabling healthcare professionals to immediately understand the reasoning behind each decision. This improves clinical validation, reduces uncertainty, and supports faster and more informed decision-making. A continuous feedback mechanism is also integrated, allowing clinicians to evaluate, correct, and refine model explanations and predictions, thereby improving system performance over time through adaptive learning. The architecture is scalable and interoperable, supporting seamless integration with existing hospital information systems and clinical workflows. By combining predictive analytics with explainability, the invention enhances diagnostic accuracy, improves clinician trust, reduces errors, and promotes safer and more reliable AI-assisted healthcare applications across diverse medical environments."

Disclaimer: Curated by HT Syndication.