Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202807,
        author = {Anitha R and Sindhuja S},
        title = {Clinical Report Interpretation Using Explainable Artificial Intelligence Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {9933-9939},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202807},
        abstract = {Electronic health records, diagnostic summaries, and other clinical documents are being generated at an increasingly large scale due to the rapid digital transformation of healthcare systems. However, these records are often highly technical and difficult for patients or non-expert users to understand. As a result, many individuals face challenges in interpreting their medical information, which can negatively impact overall health awareness and decision-making. To overcome this limitation, the paper introduces an Explainable Artificial Intelligence (XAI) framework aimed at automatically processing and simplifying medical reports. The primary goal of the system is to improve accessibility by transforming complex clinical data into clear, understandable language while also supporting knowledge-based explanations. The proposed framework follows a structured multi-stage pipeline that combines multiple AI techniques. It begins with Optical Character Recognition (OCR) to extract text from scanned or image-based medical documents. This is followed by biomedical Named Entity Recognition (NER), which identifies and categorizes key medical terms such as diseases, symptoms, medications, and procedures. Finally, transformer-based models are used to generate simplified and coherent summaries of the extracted clinical information. The system also includes a knowledge retrieval module that links identified medical entities with relevant explanations, definitions, and contextual insights. This helps users better understand medical terminology and improves the interpretability of the generated summaries. By combining extraction, summarization, and explanation, the framework ensures that medical information is not only processed but also made meaningful for end users. The effectiveness of the proposed system is validated through experimental evaluation, focusing on accuracy, readability, and user comprehension.},
        keywords = {Explainable Artificial Intelligence, Medical Report Processing, Biomedical Named Entity Recognition, Transformer-Based Summarization, Clinical Knowledge Retrieval.},
        month = {May},
        }