The article discusses the application of Natural Language Processing (NLP) and Deep Learning (DL) in improving the identification of Venous thromboembolism (VTE) from radiology reports. VTE, which includes deep vein thrombosis (DVT) and pulmonary embolism (PE), is a severe cardiovascular condition. The study proposes novel method combinations of DL methods, data augmentation, adaptive pre-trained NLP model selection, and a clinical expert NLP rule-based classifier. The model achieved an impressive 97% accuracy and 97% F1 score in predicting DVT, and a 98.3% accuracy and 98.4% F1 score in predicting PE. This research demonstrates the potential of NLP and DL in healthcare.
Publication date: 22 Sep 2023
Project Page: Not Provided
Paper: https://arxiv.org/pdf/2309.12273
