Healthcare knowledge graph construction: A systematic review of the state-of-the-art, open issues, and opportunities

Knowledge graph construction for heart failure using large language models with prompt engineering

Introduction

Constructing an accurate and comprehensive knowledge graph of specific diseases is critical for practical clinical disease diagnosis and treatment, reasoning and decision support, rehabilitation, and health management. For knowledge graph construction tasks (such as named entity recognition, relation extraction), classical BERT-based methods require a large amount of training data to ensure model performance. However, real-world medical annotation data, especially disease-specific annotation samples, are very limited. In addition, existing models do not perform well in recognizing out-of-distribution entities and relations that are not seen in the training phase.

Method

In this study, we present a novel and practical pipeline for constructing a heart failure knowledge graph using large language models and medical expert refinement. We apply prompt engineering to the three phases of schema design: schema design, information extraction, and knowledge completion. The best performance is achieved by designing task-specific prompt templates combined with the TwoStepChat approach.

Results

Experiments on two datasets show that the TwoStepChat method outperforms the Vanillia prompt and outperforms the fine-tuned BERT-based baselines. Moreover, our method saves 65% of the time compared to manual annotation and is better suited to extract the out-of-distribution information in the real world.

Clinical trial recommendations using Semantics-Based inductive inference and knowledge graph embeddings

OBJECTIVE

Designing a new clinical trial entails many decisions, such as defining a cohort and setting the study objectives to name a few, and therefore can benefit from recommendations based on exhaustive mining of past clinical trial records. This study proposes an approach based on knowledge graph embeddings and semantics-driven inductive inference for generating such recommendations.

METHOD

The proposed recommendation methodology is based on neural embeddings trained on first-of-its-kind knowledge graph constructed from clinical trials data. The methodology includes design of a knowledge graph for clinical trial data, evaluation of various knowledge graph embedding techniques for it, application of a novel inductive inference method using these embeddings, and generation of recommendations for clinical trial design. The study uses freely available data from clinicaltrials.gov and related sources.

RESULTS

The proposed approach for recommendations obtained relevance scores ranging from 70% to 83%. These scores were determined by evaluating the text similarity of recommended elements to actual elements used in clinical trials that are in progress. Furthermore, the most pertinent recommendations were consistently located towards the top of the list, indicating the effectiveness of our method.

CONCLUSION

Our study suggests that inductive inference using node semantics is a viable approach for generating recommendations using graphs neural embeddings, and that there is a potential for improvement in training graph embeddings using node semantics.

A systematic literature review of knowledge graph construction and application in education

In the dynamic landscape of modern education, the search for improved pedagogical methods, enriched learning experiences, and empowered educators remains a perpetual pursuit. In recent years, a remarkable technological innovation has asserted its dominance in education: Knowledge Graphs (KGs). These structured representations of knowledge are increasingly proving to be indispensable tools, fostering advancements driven by the growing recognition of their essential role in enriching personalised learning, curriculum design, concept mapping, and educational content recommendation systems. In this paper, a systematic literature review (SLR) has been conducted to comprehensively examine KG construction methodologies and their applications across five key domains in education. In each examined study, we highlight the specific KG functionalities, knowledge extraction techniques, knowledge base characteristics, resource requirements, evaluation criteria, and limitations. This paper distinguishes itself by offering a broad overview of KGs in education, analyzing state-of-the-art methodologies, and identifying research gaps and limitations, paving the way for future advancements.

A Data-Driven Paradigm for a Resilient and Sustainable Integrated Health Information Systems for Health Care Applications

Introduction

Many transformations and uncertainties, such as the fourth industrial revolution and pandemics, have propelled healthcare acceptance and deployment of health information systems (HIS). External and internal determinants aligning with the global course influence their deployments. At the epic is digitalization, which generates endless data that has permeated healthcare. The continuous proliferation of complex and dynamic healthcare data is the digitalization frontier in healthcare that necessitates attention.

Objective

This study explores the existing body of information on HIS for healthcare through the data lens to present a data-driven paradigm for healthcare augmentation paramount to attaining a sustainable and resilient HIS.

Method

Preferred Reporting Items for Systematic Reviews and Meta-Analyses: PRISMA-compliant in-depth literature review was conducted systematically to synthesize and analyze the literature content to ascertain the value disposition of HIS data in healthcare delivery.

Results

This study details the aspects of a data-driven paradigm for robust and sustainable HIS for health care applications. Data source, data action and decisions, data sciences techniques, serialization of data sciences techniques in the HIS, and data insight implementation and application are data-driven features expounded. These are essential data-driven paradigm building blocks that need iteration to succeed.

Discussions

Existing literature considers insurgent data in healthcare challenging, disruptive, and potentially revolutionary. This view echoes the current healthcare quandary of good and bad data availability. Thus, data-driven insights are essential for building a resilient and sustainable HIS. People, technology, and tasks dominated prior HIS frameworks, with few data-centric facets. Improving healthcare and the HIS requires identifying and integrating crucial data elements.

Conclusion

The paper presented a data-driven paradigm for a resilient and sustainable HIS. The findings show that data-driven track and components are essential to improve healthcare using data analytics insights. It provides an integrated footing for data analytics to support and effectively assist health care delivery.