Identifying incidental findings from radiology reports of trauma patients: An evaluation of automated feature representation methods. (September 2019)

• Record Type: Journal Article
• Authors: Trivedi, Gaurav; Hong, Charmgil; Dadashzadeh, Esmaeel R.; Handzel, Robert M.; Hochheiser, Harry; Visweswaran, Shyam
• Is Part Of: International journal of medical informatics. Volume 129(2019)
• Page Start: 81
• Page End: 87
• Publication Date: 2019-09
• Subjects: Automated feature representations -- Radiology reports -- Incidental findings -- Word embeddings -- Convolutional neural networks; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2019.05.021
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: Incidental findings from radiology reports can be extracted using machine learning methods. It is feasible to extract incidentals at finer levels of resolution (sentence and section level) at performance similar to that at report-level in prior work. Representing radiology reports using concepts extracted from biomedical ontologies, along with text-based features, did not result in any performance improvements. Unsupervised methods on large datasets for learning better word representations hold promise in improving performance with supervised deep learning methods on smaller datasets. Abstract: Background: Radiologic imaging of trauma patients often uncovers findings that are unrelated to the trauma. These are termed as incidental findings and identifying them in radiology examination reports is necessary for appropriate follow-up. We developed and evaluated an automated pipeline to identify incidental findings at sentence and section levels in radiology reports of trauma patients. Methods: We created an annotated dataset of 4, 181 reports and investigated automated feature representations including traditional word and clinical concept (such as SNOMED CT) representations, as well as word and concept embeddings. We evaluated these representations by using them with traditional classifiers such as logistic regression and with deep learning methods such as convolutional neural networks (CNNs). Results: The best performance was observed using word embeddings with CNNs with F 1 scores of 0.66 and 0.52 at section and sentence levels respectively. The F 1 score was statistically significantly higher for sections compared to sentences (Wilcoxon; Z < 0.001, p < 0.05). Compared to using words alone, the addition of SNOMED CT concepts did not improve performance. At the sentence level, the F 1 score improved significantly from 0.46 to 0.52 when using pre-trained embeddings (Wilcoxon; Z < 0.001, p < 0.05). Conclusion: The results show that the best performance was achieved by using embeddings with CNNs at both sentence and section levels. This provides evidence that such a pipeline is capable of accurately identifying incidental findings in radiology reports in an automated manner.