Bi-LSTM 1 (LDCT Report NLP Model)
Best-performing in-house NLP model for parsing LDCT radiology reports.
Description: An open-source Bi-LSTM NER recurrent neural network which outperformed other open-source or rule-based radiology NER models in the LDCT NER task. This model can efficiently extract clinically relevant information from lung cancer screening CT reports with high accuracy, enabling efficient audit and feedback to improve quality of patient care.
Citation
Zhang Y, Grant BMM, Hope AJ, Hung RJ, Warkentin MT, Lam ACL, Aggawal R, Xu M, Shepherd FA, Tsao MS, Xu W, Pakkal M, Liu G, McInnis MC. Using Recurrent Neural Networks to Extract High-Quality Information From Lung Cancer Screening Computerized Tomography Reports for Inter-Radiologist Audit and Feedback Quality Improvement. JCO Clin Cancer Inform. 2023 Mar;7:e2200153.