Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Maria Esther Vidal
  • Yashrajsinh Chudasama
  • Hao Huang
  • Disha Purohit
  • Maria Torrente

External Research Organisations

  • German National Library of Science and Technology (TIB)
  • Universidad Autónoma de Madrid
View graph of relations

Details

Original languageEnglish
Article number100856
Number of pages8
JournalJournal of Web Semantics
Volume84
Early online date27 Dec 2024
Publication statusPublished - Jan 2025

Abstract

Knowledge Graphs (KGs) are graph-based structures that integrate heterogeneous data, capture domain knowledge, and enable explainable AI through symbolic reasoning. This position paper examines the challenges and research opportunities in integrating KGs with neuro-symbolic AI, highlighting their potential to enhance explainability, scalability, and context-aware reasoning in hybrid AI systems. Using a lung cancer use case, we illustrate how hybrid approaches address tasks such as link prediction—uncovering hidden relationships in medical data—and counterfactual reasoning—analyzing alternative scenarios to understand causal factors. The discussion is framed around TrustKG, which demonstrates how constraint validation, causal reasoning, and user-centric communication can support transparent and reliable decision-making. Additionally, we identify current limitations of KGs, including gaps in knowledge coverage, evolving data integration challenges, and the need for improved usability and impact assessment. These insights are not limited to healthcare but extend to other domains like energy, manufacturing, and mobility, showcasing the broad applicability of KGs. Finally, we propose research directions to unlock their full potential in building robust, transparent, and widely adopted real-world applications.

Keywords

    Counterfactual prediction, KG-based applications, Knowledge Graphs, Neuro-symbolic systems, Semantic Data Management, Valid link prediction

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine. / Vidal, Maria Esther; Chudasama, Yashrajsinh; Huang, Hao et al.
In: Journal of Web Semantics, Vol. 84, 100856, 01.2025.

Research output: Contribution to journalArticleResearchpeer review

Vidal ME, Chudasama Y, Huang H, Purohit D, Torrente M. Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine. Journal of Web Semantics. 2025 Jan;84:100856. Epub 2024 Dec 27. doi: 10.1016/j.websem.2024.100856
Vidal, Maria Esther ; Chudasama, Yashrajsinh ; Huang, Hao et al. / Integrating Knowledge Graphs with Symbolic AI : The Path to Interpretable Hybrid AI Systems in Medicine. In: Journal of Web Semantics. 2025 ; Vol. 84.
Download
@article{0f9c8ebef1544f58881922e9bd7b89da,
title = "Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine",
abstract = "Knowledge Graphs (KGs) are graph-based structures that integrate heterogeneous data, capture domain knowledge, and enable explainable AI through symbolic reasoning. This position paper examines the challenges and research opportunities in integrating KGs with neuro-symbolic AI, highlighting their potential to enhance explainability, scalability, and context-aware reasoning in hybrid AI systems. Using a lung cancer use case, we illustrate how hybrid approaches address tasks such as link prediction—uncovering hidden relationships in medical data—and counterfactual reasoning—analyzing alternative scenarios to understand causal factors. The discussion is framed around TrustKG, which demonstrates how constraint validation, causal reasoning, and user-centric communication can support transparent and reliable decision-making. Additionally, we identify current limitations of KGs, including gaps in knowledge coverage, evolving data integration challenges, and the need for improved usability and impact assessment. These insights are not limited to healthcare but extend to other domains like energy, manufacturing, and mobility, showcasing the broad applicability of KGs. Finally, we propose research directions to unlock their full potential in building robust, transparent, and widely adopted real-world applications.",
keywords = "Counterfactual prediction, KG-based applications, Knowledge Graphs, Neuro-symbolic systems, Semantic Data Management, Valid link prediction",
author = "Vidal, {Maria Esther} and Yashrajsinh Chudasama and Hao Huang and Disha Purohit and Maria Torrente",
note = "Publisher Copyright: {\textcopyright} 2024",
year = "2025",
month = jan,
doi = "10.1016/j.websem.2024.100856",
language = "English",
volume = "84",
journal = "Journal of Web Semantics",
issn = "1570-8268",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Integrating Knowledge Graphs with Symbolic AI

T2 - The Path to Interpretable Hybrid AI Systems in Medicine

AU - Vidal, Maria Esther

AU - Chudasama, Yashrajsinh

AU - Huang, Hao

AU - Purohit, Disha

AU - Torrente, Maria

N1 - Publisher Copyright: © 2024

PY - 2025/1

Y1 - 2025/1

N2 - Knowledge Graphs (KGs) are graph-based structures that integrate heterogeneous data, capture domain knowledge, and enable explainable AI through symbolic reasoning. This position paper examines the challenges and research opportunities in integrating KGs with neuro-symbolic AI, highlighting their potential to enhance explainability, scalability, and context-aware reasoning in hybrid AI systems. Using a lung cancer use case, we illustrate how hybrid approaches address tasks such as link prediction—uncovering hidden relationships in medical data—and counterfactual reasoning—analyzing alternative scenarios to understand causal factors. The discussion is framed around TrustKG, which demonstrates how constraint validation, causal reasoning, and user-centric communication can support transparent and reliable decision-making. Additionally, we identify current limitations of KGs, including gaps in knowledge coverage, evolving data integration challenges, and the need for improved usability and impact assessment. These insights are not limited to healthcare but extend to other domains like energy, manufacturing, and mobility, showcasing the broad applicability of KGs. Finally, we propose research directions to unlock their full potential in building robust, transparent, and widely adopted real-world applications.

AB - Knowledge Graphs (KGs) are graph-based structures that integrate heterogeneous data, capture domain knowledge, and enable explainable AI through symbolic reasoning. This position paper examines the challenges and research opportunities in integrating KGs with neuro-symbolic AI, highlighting their potential to enhance explainability, scalability, and context-aware reasoning in hybrid AI systems. Using a lung cancer use case, we illustrate how hybrid approaches address tasks such as link prediction—uncovering hidden relationships in medical data—and counterfactual reasoning—analyzing alternative scenarios to understand causal factors. The discussion is framed around TrustKG, which demonstrates how constraint validation, causal reasoning, and user-centric communication can support transparent and reliable decision-making. Additionally, we identify current limitations of KGs, including gaps in knowledge coverage, evolving data integration challenges, and the need for improved usability and impact assessment. These insights are not limited to healthcare but extend to other domains like energy, manufacturing, and mobility, showcasing the broad applicability of KGs. Finally, we propose research directions to unlock their full potential in building robust, transparent, and widely adopted real-world applications.

KW - Counterfactual prediction

KW - KG-based applications

KW - Knowledge Graphs

KW - Neuro-symbolic systems

KW - Semantic Data Management

KW - Valid link prediction

UR - http://www.scopus.com/inward/record.url?scp=85213232059&partnerID=8YFLogxK

U2 - 10.1016/j.websem.2024.100856

DO - 10.1016/j.websem.2024.100856

M3 - Article

AN - SCOPUS:85213232059

VL - 84

JO - Journal of Web Semantics

JF - Journal of Web Semantics

SN - 1570-8268

M1 - 100856

ER -