Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Neural network language models, such as BERT, can be used for information extraction from medical texts with unstructured free text. These models can be pre-trained on a large corpus to learn the language and characteristics of the relevant domain and then fine-tuned with labeled data for a specific task. We propose a pipeline using human-in-the-loop labeling to create annotated data for Estonian healthcare information extraction. This method is particularly useful for low-resource languages and is more accessible to those in the medical field than rule-based methods like regular expressions.

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI230281DOI Listing

Publication Analysis

Top Keywords

extraction medical
8
medical texts
8
human-in-the-loop labeling
8
texts bert
4
bert human-in-the-loop
4
labeling neural
4
neural network
4
network language
4
language models
4
models bert
4

Similar Publications

Obsessive-compulsive disorder (OCD) is a chronic and disabling condition affecting approximately 3.5% of the global population, with diagnosis on average delayed by 7.1 years or often confounded with other psychiatric disorders.

View Article and Find Full Text PDF

This study was conducted to investigate the techniques and complications of enlarged uterine extraction during minimally invasive surgery for uterine malignancy. The electronic medical record was queried for patients with uterine malignancy and enlarged uterus (≥ 250 g) who underwent primary hysterectomy with laparoscopic or robotic approach. Statistical analysis was performed using Fisher's exact test for categorical variables and Kruskal-Wallis test for continuous variables.

View Article and Find Full Text PDF

The essential cofactor coenzyme A (CoASH) and its thioester derivatives (acyl-CoAs) have pivotal roles in cellular metabolism. However, the mechanism by which different acyl-CoAs are accurately partitioned into different subcellular compartments to support site-specific reactions, and the physiological impact of such compartmentalization, remain poorly understood. Here, we report an optimized liquid chromatography-mass spectrometry-based pan-chain acyl-CoA extraction and profiling method that enables a robust detection of 33 cellular and 23 mitochondrial acyl-CoAs from cultured human cells.

View Article and Find Full Text PDF

Introduction: Metastatic breast cancer (mBC) is a major global health challenge. Antibody-drug conjugates (ADCs), including trastuzumab emtansine (T-DM1), trastuzumab deruxtecan (T-DXd), and sacituzumab govitecan (SG), offer clinical benefits but are associated with high costs, making cost-effectiveness assessments essential for policy decisions.

Methods: This systematic review analyzed economic evaluations comparing T-DM1, T-DXd, and SG with conventional treatments in breast cancer.

View Article and Find Full Text PDF

Background: Heparin-induced thrombocytopenia (HIT) is a severe primary hypercoagulable disorder, particularly concerning in hemodialysis (HD) patients frequently exposed to heparin. Fondaparinux has emerged as a potential alternative anticoagulant, though supporting evidence is limited. This systematic review aimed to evaluate the safety and efficacy of fondaparinux in HD patients with HIT.

View Article and Find Full Text PDF