The field of medical research is witnessing significant advancements in the development of knowledge graphs and large language models. These innovations are transforming the way medical information is represented, retrieved, and utilized. Recent studies have focused on creating knowledge graphs that integrate medical ontologies with clinical data, enabling robust code embeddings and improved predictive outcomes. The integration of large language models with these knowledge graphs has shown great promise in uncovering disease relationships, predicting clinical outcomes, and enhancing clinically-driven missing data recovery algorithms. Noteworthy papers in this area include: H-DDx, which introduces a hierarchical evaluation framework for differential diagnosis, and KEEP, which presents an efficient framework for integrating medical ontologies with clinical data. These developments have the potential to revolutionize the field of medical research, enabling more accurate diagnoses, personalized medicine, and hypothesis formulation in cognitive neuroscience.
Advances in Medical Knowledge Graphs and Language Models
Sources
Semantic Similarity in Radiology Reports via LLMs and NER
LLM, Reporting In! Medical Information Extraction Across Prompting, Fine-tuning and Post-correction
H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis
On Using Large Language Models to Enhance Clinically-Driven Missing Data Recovery Algorithms in Electronic Health Records
Revealing Interconnections between Diseases: from Statistical Methods to Large Language Models
KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings
Flavonoid Fusion: Creating a Knowledge Graph to Unveil the Interplay Between Food and Health
MultiCNKG: Integrating Cognitive Neuroscience, Gene, and Disease Knowledge Graphs Using Large Language Models