Title: MediSum: A NLP Framework for Automatic Summarization of Medical Reports


Authors: Tanvi Shrivastava, Vanshika Patel, Yashraj Singh Thakur, Vedika Butani


Published in: Volume 3 Issue 1 Jan June 2026, Page No.198-200


DOI: 10.63844/IJAITR.v3.i1.2026.198-200 cite


Keywords:Natural Language Processing, Machine Learning, Medical Text Summarization, Named Entity Recognition, Abstractive Methods, OCR, Artificial Intelligence.


Abstract: The rapid growth of clinical documentation has made it harder for healthcare professionals to interpret patient records efficiently. Long and complicated reports also create problems for patients, often leading to delays in important medical decisions. To tackle this issue, this research suggests a Medical Report Summarizer that uses Natural Language Processing (NLP) and Machine Learning (ML) techniques to produce clear, contextually accurate summaries of medical texts. The framework includes steps like data preprocessing, entity recognition, and abstractive summarization to pull out and restate key insights, such as diagnoses, lab results, treatment details, and recommended follow-ups. Built in Python with modern NLP frameworks, the system can handle various medical report formats while maintaining critical clinical meaning. Evaluation results show marked improvements in readability and efficiency compared to conventional extractive methods, achieving over a 60% reduction in review time. The tool also features report comparison, severity analysis, and reminder scheduling. Future upgrades plan to include voice input, support for multiple languages, and cloud access for easy integration into hospital information systems.


Download PDF