A systematic review of natural language processing applied to radiology reports

• Published in: BMC medical informatics and decision making Vol. 21; no. 1; pp. 179 - 18
• Main Authors: Casey, Arlene, Davidson, Emma, Poon, Michael, Dong, Hang, Duma, Daniel, Grivas, Andreas, Grover, Claire, Suárez-Paniagua, Víctor, Tobin, Richard, Whiteley, William, Wu, Honghan, Alex, Beatrice
• Format: Journal Article
• Language: English
• Published: London BioMed Central 03.06.2021; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Analysis; Automation; Citation analysis; Computational linguistics; Datasets; Deep learning; Diagnostic imaging; Documents; Electronic health records; Evaluation; Health aspects; Health care; Health Informatics; Heterogeneity; Humans; Information Systems and Communication Service; Language; Language processing; Learning algorithms; Machine Learning; Management of Computing and Information Systems; Medical imaging; Medical research; Medicine; Medicine & Public Health; Metadata; Natural language interfaces; Natural Language Processing; Radiologists; Radiology; Radiology Information Systems; Reproducibility of Results; Systematic review; United Kingdom; Radiology; Systematic review; Natural language processing
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-021-01533-7

Background Natural language processing (NLP) has a significant role in advancing healthcare and has been found to be key in extracting structured information from radiology reports. Understanding recent developments in NLP application to radiology is of significance but recent reviews on this are limited. This study systematically assesses and quantifies recent literature in NLP applied to radiology reports. Methods We conduct an automated literature search yielding 4836 results using automated filtering, metadata enriching steps and citation search combined with manual review. Our analysis is based on 21 variables including radiology characteristics, NLP methodology, performance, study, and clinical application characteristics. Results We present a comprehensive analysis of the 164 publications retrieved with publications in 2019 almost triple those in 2015. Each publication is categorised into one of 6 clinical application categories. Deep learning use increases in the period but conventional machine learning approaches are still prevalent. Deep learning remains challenged when data is scarce and there is little evidence of adoption into clinical practice. Despite 17% of studies reporting greater than 0.85 F1 scores, it is hard to comparatively evaluate these approaches given that most of them use different datasets. Only 14 studies made their data and 15 their code available with 10 externally validating results. Conclusions Automated understanding of clinical narratives of the radiology reports has the potential to enhance the healthcare process and we show that research in this field continues to grow. Reproducibility and explainability of models are important if the domain is to move applications into clinical use. More could be done to share code enabling validation of methods on different institutional data and to reduce heterogeneity in reporting of study properties allowing inter-study comparisons. Our results have significance for researchers in the field providing a systematic synthesis of existing work to build on, identify gaps, opportunities for collaboration and avoid duplication.