Understanding the performance and reliability of NLP tools: a comparison of four NLP tools predicting stroke phenotypes in radiology reports

• Main Authors: Arlene Casey (Author), Emma Davidson (Author), Claire Grover (Author), Richard Tobin (Author), Andreas Grivas (Author), Huayu Zhang (Author), Patrick Schrempf (Author), Alison Q. O'Neil (Author), Liam Lee (Author), Michael Walsh (Author), Freya Pellie (Author), Karen Ferguson (Author), Vera Cvoro (Author), Honghan Wu (Author), Heather Whalley (Author), Grant Mair (Author), William Whiteley (Author), Beatrice Alex (Author)
• Format: Book
• Published: Frontiers Media S.A., 2023-09-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.

BackgroundNatural language processing (NLP) has the potential to automate the reading of radiology reports, but there is a need to demonstrate that NLP methods are adaptable and reliable for use in real-world clinical applications.MethodsWe tested the F1 score, precision, and recall to compare NLP t...