EHR coding with hybrid attention and features propagation on disease knowledge graph.

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. we also use a long sequence encoder to get EHR document representation. most importantly ►KGENet leverages multi-view disease attributes and structured disease relationships for knowledge enhancement through hybrid attention and graph propagation ►Respectively. furthermore ►The above processes can provide attribute-aware and relationship-augmented explainability for the model prediction results based on our disease knowledge graph. experiments conducted on the MIMIC-III benchmark dataset show that KGENet outperforms state-of-the-art models in both model effectiveness and explainability Electronic health record (EHR) coding assigns International Classification of Diseases (ICD) codes to each EHR document. These standard medical codes represent diagnoses or procedures and play a critical role in medical applications. However, EHR is a long medical text that is difficult to represent, the ICD code label space is large, and the labels have an extremely unbalanced distribution. These factors pose challenges to automatic EHR coding. Previous studies have not explored the disease attributes (e.g., symptoms, tests, medications) of ICD codes and the disease relationships (e.g., causes, risk factors, comorbidities) between them. In addition, the important roles of medical.

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.

Comparison of Clinical Efficacy of Neoadjuvant Chemoradiation Therapy Between Lower and Higher Radiation Doses for Carcinoma of the Esophagus and Gastroesophageal Junction: A Systematic Review.

PURPOSE: 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 50.4 Gy in 28 fractions that were published until July 2019, when the search was performed. Physical dose distributions were converted to biologically equivalent doses (BEDs), which were described in units of gray (alpha/beta). Pooled rates of overall survival (OS), progression-free survival (PFS), failure patterns, and toxicities were compared between lower-dose radiation therapy (LDRT; BED ≤48.85 Gy10) and higher-dose radiation therapy (HDRT; BED >48.85 Gy10) for patients treated with nCRT. RESULTS: A total of 110 studies with 7577 EC/GEJ patients receiving nCRT were included in this pooled analysis. Both the PFS and OS rates of patients receiving LDRT were significantly higher than those of patients receiving HDRT. Patients receiving LDRT had improved safety regarding treatment-related adverse events and lower distant failure rates than patients receiving HDRT. Utilization of modern radiation therapy (RT) techniques, including 3-dimensional conformal RT and intensity modulated RT, was associated with improved oncologic outcomes compared with 2-dimensional methods. Subgroup analysis showed that EC/GEJ patients receiving conventionally fractionated radiation to a dose of 40.0 to 41.4 Gy in 20-23 fractions showed improved OS compared with those receiving radiation above this dose. CONCLUSIONS: Based on the limited data, nCRT using BED ≤48.85 Gy10 was suitable for locoregionally advanced, resectable EC/GEJ. A total dose of 40.0 to 41.4 Gy in 20 to 23 fractions using modern RT techniques might provide the optimal therapeutic ratio.