Development and web deployment of an automated neuroradiology MRI protocoling tool with natural language processing

BMC Medical Informatics and Decision Making

Jae Ho Sohn¹  Benjamin Laguna¹  Thienkhai Vu¹  Youngho Seo¹  Timothy L. Chen¹  Jared Narvid¹  Gunvant R. Chaudhari¹  Shourya Munjal²  Yeshwant Reddy Chillakuru³ 

[1] Radiology & Biomedical Imaging, University of California San Francisco (UCSF), 505 Parnassus Ave, 94158, San Francisco, CA, USA;Radiology & Biomedical Imaging, University of California San Francisco (UCSF), 505 Parnassus Ave, 94158, San Francisco, CA, USA;Rice University, 6100 Main St, 77005, Houston, TX, USA;Radiology & Biomedical Imaging, University of California San Francisco (UCSF), 505 Parnassus Ave, 94158, San Francisco, CA, USA;The George Washington University School of Medicine and Health Sciences, 2300 I St NW, 20052, Washington, DC, USA;

关键词: Natural language processing;    Protocol;    Automation;    Neuroimaging;   

DOI  :  10.1186/s12911-021-01574-y

来源: Springer

【 摘 要 】

BackgroundA systematic approach to MRI protocol assignment is essential for the efficient delivery of safe patient care. Advances in natural language processing (NLP) allow for the development of accurate automated protocol assignment. We aim to develop, evaluate, and deploy an NLP model that automates protocol assignment, given the clinician indication text.MethodsWe collected 7139 spine MRI protocols (routine or contrast) and 990 head MRI protocols (routine brain, contrast brain, or other) from a single institution. Protocols were split into training (n = 4997 for spine MRI; n = 839 for head MRI), validation (n = 1071 for spine MRI, fivefold cross-validation used for head MRI), and test (n = 1071 for spine MRI; n = 151 for head MRI) sets. fastText and XGBoost were used to develop 2 NLP models to classify spine and head MRI protocols, respectively. A Flask-based web app was developed to be deployed via Heroku.ResultsThe spine MRI model had an accuracy of 83.38% and a receiver operator characteristic area under the curve (ROC-AUC) of 0.8873. The head MRI model had an accuracy of 85.43% with a routine brain protocol ROC-AUC of 0.9463 and contrast brain protocol ROC-AUC of 0.9284. Cancer, infectious, and inflammatory related keywords were associated with contrast administration. Structural anatomic abnormalities and stroke/altered mental status were indicative of routine spine and brain MRI, respectively. Error analysis revealed increasing the sample size may improve performance for head MRI protocols. A web version of the model is provided for demonstration and deployment.ConclusionWe developed and web-deployed two NLP models that accurately predict spine and head MRI protocol assignment, which could improve radiology workflow efficiency.

【 授权许可】

CC BY