Publications by authors named "Yixun Gu"
Article Synopsis
- Constructing a knowledge graph for diseases, specifically heart failure, is important for enhancing clinical diagnosis, treatment, and health management, but current methods often struggle with limited training data and out-of-distribution entities.* -
- This study introduces an innovative pipeline that uses large language models, prompt engineering, and expert refinement to improve the design and extraction phases of knowledge graph construction.* -
- Results show the proposed TwoStepChat method significantly outperforms traditional methods, saving 65% of annotation time and effectively handling information not present in training data.*
EHR coding with hybrid attention and features propagation on disease knowledge graph.
Artif Intell Med
August 2024
And sentences associated with these attributes and relationships have been neglected. in this paper ►We propose an end-to-end model called Knowledge Graph Enhanced neural network (KGENet) to address the above shortcomings. specifically ►We first construct a disease knowledge graph that focuses on the multi-view disease attributes of ICD codes and the disease relationships between these codes.
View Article and Find Full Text PDFPurpose: Neoadjuvant concurrent chemoradiation therapy (nCRT) plus surgery has been a standard treatment for locoregionally advanced esophageal cancer and carcinoma of the gastroesophageal junction (EC/GEJ), but the optimal preoperative radiation dose is still unclear. We performed this systematic review to explore the treatment efficacy and toxicity of different radiation dose levels and find an optimal dose-fractionation strategy in EC/GEJ patients receiving nCRT.
Methods And Materials: Embase and Ovid Medline were searched for articles involving cases of operable squamous and adenocarcinoma of the esophagus and GEJ in which patients received nCRT up to a dose of 50.