Skip to main content
Journal cover image

ClotCatcher: a novel natural language model to accurately adjudicate venous thromboembolism from radiology reports.

Publication ,  Journal Article
Wang, J; de Vale, JS; Gupta, S; Upadhyaya, P; Lisboa, FA; Schobel, SA; Elster, EA; Dente, CJ; Buchman, TG; Kamaleswaran, R
Published in: BMC Med Inform Decis Mak
November 16, 2023

INTRODUCTION: Accurate identification of venous thromboembolism (VTE) is critical to develop replicable epidemiological studies and rigorous predictions models. Traditionally, VTE studies have relied on international classification of diseases (ICD) codes which are inaccurate - leading to misclassification bias. Here, we developed ClotCatcher, a novel deep learning model that uses natural language processing to detect VTE from radiology reports. METHODS: Radiology reports to detect VTE were obtained from patients admitted to Emory University Hospital (EUH) and Grady Memorial Hospital (GMH). Data augmentation was performed using the Google PEGASUS paraphraser. This data was then used to fine-tune ClotCatcher, a novel deep learning model. ClotCatcher was validated on both the EUH dataset alone and GMH dataset alone. RESULTS: The dataset contained 1358 studies from EUH and 915 studies from GMH (n = 2273). The dataset contained 1506 ultrasound studies with 528 (35.1%) studies positive for VTE, and 767 CT studies with 91 (11.9%) positive for VTE. When validated on the EUH dataset, ClotCatcher performed best (AUC = 0.980) when trained on both EUH and GMH dataset without paraphrasing. When validated on the GMH dataset, ClotCatcher performed best (AUC = 0.995) when trained on both EUH and GMH dataset with paraphrasing. CONCLUSION: ClotCatcher, a novel deep learning model with data augmentation rapidly and accurately adjudicated the presence of VTE from radiology reports. Applying ClotCatcher to large databases would allow for rapid and accurate adjudication of incident VTE. This would reduce misclassification bias and form the foundation for future studies to estimate individual risk for patient to develop incident VTE.

Duke Scholars

Published In

BMC Med Inform Decis Mak

DOI

EISSN

1472-6947

Publication Date

November 16, 2023

Volume

23

Issue

1

Start / End Page

262

Location

England

Related Subject Headings

  • Venous Thromboembolism
  • Radiology
  • Natural Language Processing
  • Medical Informatics
  • Humans
  • Hospitals, University
  • Hospitalization
  • 4203 Health services and systems
  • 1103 Clinical Sciences
  • 0806 Information Systems
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, J., de Vale, J. S., Gupta, S., Upadhyaya, P., Lisboa, F. A., Schobel, S. A., … Kamaleswaran, R. (2023). ClotCatcher: a novel natural language model to accurately adjudicate venous thromboembolism from radiology reports. BMC Med Inform Decis Mak, 23(1), 262. https://doi.org/10.1186/s12911-023-02369-z
Wang, Jeffrey, Joao Souza de Vale, Saransh Gupta, Pulakesh Upadhyaya, Felipe A. Lisboa, Seth A. Schobel, Eric A. Elster, Christopher J. Dente, Timothy G. Buchman, and Rishikesan Kamaleswaran. “ClotCatcher: a novel natural language model to accurately adjudicate venous thromboembolism from radiology reports.BMC Med Inform Decis Mak 23, no. 1 (November 16, 2023): 262. https://doi.org/10.1186/s12911-023-02369-z.
Wang J, de Vale JS, Gupta S, Upadhyaya P, Lisboa FA, Schobel SA, et al. ClotCatcher: a novel natural language model to accurately adjudicate venous thromboembolism from radiology reports. BMC Med Inform Decis Mak. 2023 Nov 16;23(1):262.
Wang, Jeffrey, et al. “ClotCatcher: a novel natural language model to accurately adjudicate venous thromboembolism from radiology reports.BMC Med Inform Decis Mak, vol. 23, no. 1, Nov. 2023, p. 262. Pubmed, doi:10.1186/s12911-023-02369-z.
Wang J, de Vale JS, Gupta S, Upadhyaya P, Lisboa FA, Schobel SA, Elster EA, Dente CJ, Buchman TG, Kamaleswaran R. ClotCatcher: a novel natural language model to accurately adjudicate venous thromboembolism from radiology reports. BMC Med Inform Decis Mak. 2023 Nov 16;23(1):262.
Journal cover image

Published In

BMC Med Inform Decis Mak

DOI

EISSN

1472-6947

Publication Date

November 16, 2023

Volume

23

Issue

1

Start / End Page

262

Location

England

Related Subject Headings

  • Venous Thromboembolism
  • Radiology
  • Natural Language Processing
  • Medical Informatics
  • Humans
  • Hospitals, University
  • Hospitalization
  • 4203 Health services and systems
  • 1103 Clinical Sciences
  • 0806 Information Systems