Automated decision making in Barrett's oesophagus : development and deployment of a natural language processing tool
Zecevic, Agathe Jackson, Laurence Zhang, Xinyue Pavlidis, Polychronis Dunn, Jason Ahmed, Shahd Visaggi, Pierfrancesco YoonusNizar, Zanil Roberts, Angus
Zecevic, Agathe
Jackson, Laurence
Zhang, Xinyue
Pavlidis, Polychronis
Dunn, Jason
Ahmed, Shahd
Visaggi, Pierfrancesco
YoonusNizar, Zanil
Roberts, Angus
Citations
Altmetric:
Affiliation
Guy's and St. Thomas' NHS Foundation Trust, King's College London; Sandwell and West Birmingham NHS Trust; King's College Hospital; et al.
Other Contributors
Publication date
2024-11-07
Subject
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Manual decisions regarding the timing of surveillance endoscopy for premalignant Barrett's oesophagus (BO) is error-prone. This leads to inefficient resource usage and safety risks. To automate decision-making, we fine-tuned Bidirectional Encoder Representations from Transformers (BERT) models to categorize BO length (EndoBERT) and worst histopathological grade (PathBERT) on 4,831 endoscopy and 4,581 pathology reports from Guy's and St Thomas' Hospital (GSTT). The accuracies for EndoBERT test sets from GSTT, King's College Hospital (KCH), and Sandwell and West Birmingham Hospitals (SWB) were 0.95, 0.86, and 0.99, respectively. Average accuracies for PathBERT were 0.93, 0.91, and 0.92, respectively. A retrospective analysis of 1640 GSTT reports revealed a 27% discrepancy between endoscopists' decisions and model recommendations. This study underscores the development and deployment of NLP-based software in BO surveillance, demonstrating high performance at multiple sites. The analysis emphasizes the potential efficiency of automation in enhancing precision and guideline adherence in clinical decision-making.
Citation
Zecevic A, Jackson L, Zhang X, Pavlidis P, Dunn J, Trudgill N, Ahmed S, Visaggi P, YoonusNizar Z, Roberts A, Zeki SS. Automated decision making in Barrett's oesophagus: development and deployment of a natural language processing tool. NPJ Digit Med. 2024 Nov 7;7(1):312. doi: 10.1038/s41746-024-01302-6.
Type
Article