Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Natural Language Processing for Cardiology: A Narrative Review

Kailai Yang, Yan Leng, Xin Zhang, Tianlin Zhang, Paul Thompson, Bernard Keavney, Maciej Tomaszewski, Sophia Ananiadou

TL;DR

Cardiovascular diseases generate vast amounts of unstructured text across EHRs, imaging reports, and patient interactions. The paper conducts a comprehensive 2014–2025 narrative review of NLP applications in cardiology, surveying 258–265 studies from six databases and detailing data sources, tasks, diseases, and NLP methods. It documents a clear methodological evolution from rule-based approaches to traditional ML, deep learning, and modern large language models (LLMs), with a notable rise of text-guided generation and retrieval-augmented generation. Key challenges include interpretability, trust, and data privacy, while future work emphasizes interpretable LLMs, multi-modal data integration, and open-source tooling to democratize cardiology NLP and enhance clinical impact. Overall, the review positions LLMs as the dominant current paradigm in cardiology NLP, while advocating for frameworks that ensure transparency, regulatory compliance, and interoperability.

Abstract

Cardiovascular diseases are becoming increasingly prevalent in modern society, with a profound impact on global health and well-being. These Cardiovascular disorders are complex and multifactorial, influenced by genetic predispositions, lifestyle choices, and diverse socioeconomic and clinical factors. Information about these interrelated factors is dispersed across multiple types of textual data, including patient narratives, medical records, and scientific literature. Natural language processing (NLP) has emerged as a powerful approach for analysing such unstructured data, enabling healthcare professionals and researchers to gain deeper insights that may transform the diagnosis, treatment, and prevention of cardiac disorders. This review provides a comprehensive overview of NLP research in cardiology from 2014 to 2025. We systematically searched six literature databases for studies describing NLP applications across a range of cardiovascular diseases. After a rigorous screening process, we identified 265 relevant articles. Each study was analysed across multiple dimensions, including NLP paradigms, cardiology-related tasks, disease types, and data sources. Our findings reveal substantial diversity within these dimensions, reflecting the breadth and evolution of NLP research in cardiology. A temporal analysis further highlights methodological trends, showing a progression from rule-based systems to large language models. Finally, we discuss key challenges and future directions, such as developing interpretable LLMs and integrating multimodal data. To the best of our knowledge, this review represents the most comprehensive synthesis of NLP research in cardiology to date.

Natural Language Processing for Cardiology: A Narrative Review

TL;DR

Cardiovascular diseases generate vast amounts of unstructured text across EHRs, imaging reports, and patient interactions. The paper conducts a comprehensive 2014–2025 narrative review of NLP applications in cardiology, surveying 258–265 studies from six databases and detailing data sources, tasks, diseases, and NLP methods. It documents a clear methodological evolution from rule-based approaches to traditional ML, deep learning, and modern large language models (LLMs), with a notable rise of text-guided generation and retrieval-augmented generation. Key challenges include interpretability, trust, and data privacy, while future work emphasizes interpretable LLMs, multi-modal data integration, and open-source tooling to democratize cardiology NLP and enhance clinical impact. Overall, the review positions LLMs as the dominant current paradigm in cardiology NLP, while advocating for frameworks that ensure transparency, regulatory compliance, and interoperability.

Abstract

Cardiovascular diseases are becoming increasingly prevalent in modern society, with a profound impact on global health and well-being. These Cardiovascular disorders are complex and multifactorial, influenced by genetic predispositions, lifestyle choices, and diverse socioeconomic and clinical factors. Information about these interrelated factors is dispersed across multiple types of textual data, including patient narratives, medical records, and scientific literature. Natural language processing (NLP) has emerged as a powerful approach for analysing such unstructured data, enabling healthcare professionals and researchers to gain deeper insights that may transform the diagnosis, treatment, and prevention of cardiac disorders. This review provides a comprehensive overview of NLP research in cardiology from 2014 to 2025. We systematically searched six literature databases for studies describing NLP applications across a range of cardiovascular diseases. After a rigorous screening process, we identified 265 relevant articles. Each study was analysed across multiple dimensions, including NLP paradigms, cardiology-related tasks, disease types, and data sources. Our findings reveal substantial diversity within these dimensions, reflecting the breadth and evolution of NLP research in cardiology. A temporal analysis further highlights methodological trends, showing a progression from rule-based systems to large language models. Finally, we discuss key challenges and future directions, such as developing interpretable LLMs and integrating multimodal data. To the best of our knowledge, this review represents the most comprehensive synthesis of NLP research in cardiology to date.
Paper Structure (46 sections, 12 figures, 3 tables)

This paper contains 46 sections, 12 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Search Methodology
  3. Search strategy
  4. Filtering strategy
  5. Findings
  6. Data Sources
  7. Top-level Category
  8. Electronic Health Records (EHRs)
  9. Published Literature and Medical Databases
  10. Synthetic or Generated Data
  11. Clinical Trial Data
  12. Telehealth Data
  13. Patient-reported Outcomes and Surveys
  14. Home Healthcare Data
  15. Administrative data
  16. ...and 31 more sections

Figures (12)

  • Figure 1: A three-stage pipeline of the article selection process.
  • Figure 2: A general overview of the diversity of research reported.
  • Figure 3: The hierarchical dataset classification schema for classification of data sources.
  • Figure 4: Pie chart of the distribution of data source categories in Cardiology NLP research.
  • Figure 5: Distribution of different subcategories of EHRs.
  • ...and 7 more figures