Enhancing Medical Text Summarization using Transformer-Based NLP Models for Clinical Decision Support

Journal Title: Engineering and Technology Journal - Year 2025, Vol 10, Issue 05

Abstract

Medical text summarization plays a crucial role in clinical decision support by enabling healthcare professionals to quickly access essential information from vast amounts of unstructured medical texts. With the rapid advancements in Natural Language Processing (NLP), transformer-based models have emerged as powerful tools for generating high-quality summaries. This paper investigates the effectiveness of state-of-the-art transformer models, such as BERT, GPT, and T5, in summarizing medical texts while preserving critical information. We conduct comprehensive evaluations using benchmark datasets and assess the performance of these models in terms of coherence, relevance, and readability. The experimental results demonstrate that transformer-based models significantly outperform traditional extractive and abstractive summarization techniques, offering more accurate and contextually meaningful summaries. Furthermore, we highlight the importance of domain-specific pretraining and fine-tuning to enhance model performance in medical applications. This study provides valuable insights into the practical deployment of transformer-based summarization models in healthcare settings, ultimately contributing to improved clinical workflows and informed decision-making.

Authors and Affiliations

Mohammed Hashim Younis, Ibrahim M. I. Zebari,

Keywords

Related Articles

Systematic Review of AI-Augmented Refactoring and Code Validation Tools in Aviation Technology Platforms

As aviation technology platforms become increasingly complex and software-intensive, ensuring code quality, maintainability, and compliance with stringent safety standards has become a critical priority. This systematic...

MECHANICAL BEHAVIOUR OF FERROCEMENT LIGHTWEIGHT BANANA FIBRE CONCRETE UNDER UNIAXIAL BENDING

To obtain lightweight and environmentally friendly building materials that can be produced quickly at low cost, among others, can be obtained through the use of natural fiber based ferrocement concrete technology. The us...

Big Data Cloud Computing and AI-Driven Digital Marketing in Enterprise Systems

The integration of Big Data, Cloud Computing, and Artificial Intelligence (AI) has significantly transformed digital marketing and modern enterprise systems. These technologies enable advanced data analytics, predictive...

Designing Typical Malang Handicraft Products Through the Utilization of Sawdust at Micro and Small Enterprise

This article examines the use of sawdust as a souvenir product with resin material at MSEs Berdikari Meubel Nusantara, a furniture manufacturer specializing in high quality products made from mahogany, pine, and teak. Th...

Effects of Information and Communication Technology Adoption on University Competitive Advantage via Education Quality a Field Study on Science & Technology and Hadhramout Universities

The current study aimed to determine the effect of information and communication technology adoption on university competitive advantage via education quality in Yemenis Universities. For the purposes of this study, the...

Download PDF file
  • EP ID EP768095
  • DOI 10.47191/etj/v10i05.55
  • Views 21
  • Downloads 0

How To Cite

Mohammed Hashim Younis, Ibrahim M. I. Zebari, (2025). Enhancing Medical Text Summarization using Transformer-Based NLP Models for Clinical Decision Support. Engineering and Technology Journal, 10(05), -. https://europub.co.uk/articles/-A-768095