Abstract
AbstractThough sophisticated algorithms have been developed for the classification of free-text radiology reports for pulmonary embolism (PE), their overall generalizability remains unvalidated given limitations in sample size and data homogeneity. We developed and validated a highly generalizable deep-learning based NLP algorithm for this purpose with data sourced from over 2,000 hospital sites and 500 radiologists. The algorithm achieved an AUCROC of 0.995 on chest angiography studies and 0.994 on non-angiography studies for the presence or absence of PE. The high accuracy achieved on this large and heterogeneous dataset allows for the possibility of application in large multi-center radiology practices as well as for deployment at novel sites without significant degradation in performance.
Publisher
Cold Spring Harbor Laboratory
Reference11 articles.
1. Epidemiology, Pathophysiology, Stratification, and Natural History of Pulmonary Embolism;Tech Vasc Interv Radiol,2017
2. Evaluating Report Text Variation and Informativeness: Natural Language Processing of CT Chest Imaging for Pulmonary Embolism;J Am Coll Radiol,2018
3. A natural language processing algorithm to define a venous thromboembolism phenotype;AMIA Annu Symp Proc,2013
4. Document-level classification of CT pulmonary angiography reports based on an extension of the ConText algorithm
5. Deep Learning to Classify Radiology Free-Text Reports
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献