Natural language processing in urology: Automated extraction of clinical information from histopathology reports of uro-oncology procedures

• Published in: Heliyon 2023-04, Vol.9 (4), p.e14793-e14793, Article e14793
• Main Authors: Huang, Honghong, Lim, Fiona Xin Yi, Gu, Gary Tianyu, Han, Matthew Jiangchou, Fang, Andrew Hao Sen, Chia, Elian Hui San, Bei, Eileen Yen Tze, Tham, Sarah Zhuling, Ho, Henry Sun Sien, Yuen, John Shyi Peng, Sun, Aixin, Lim, Jay Kheng Sit
• Format: Article
• Language: English
• Subjects: Cancer registry; Deep learning; Machine learning; Natural language processing; Uro-oncology histology reports
• ISSN: 2405-8440; 2405-8440
• DOI: 10.1016/j.heliyon.2023.e14793

We aimed to automate routine extraction of clinically relevant unstructured information from uro-oncological histopathology reports by applying rule-based and machine learning (ML)/deep learning (DL) methods to develop an oncology focused natural language processing (NLP) algorithm. Our algorithm employs a combination of a rule-based approach and support vector machines/neural networks (BioBert/Clinical BERT), and is optimised for accuracy. We randomly extracted 5772 uro-oncological histology reports from 2008 to 2018 from electronic health records (EHRs) and split the data into training and validation datasets in an 80:20 ratio. The training dataset was annotated by medical professionals and reviewed by cancer registrars. The validation dataset was annotated by cancer registrars and defined as the gold standard with which the algorithm outcomes were compared. The accuracy of NLP-parsed data was matched against these human annotation results. We defined an accuracy rate of >95% as “acceptable” by professional human extraction, as per our cancer registry definition. There were 11 extraction variables in 268 free-text reports. We achieved an accuracy rate of between 61.2% and 99.0% using our algorithm. Of the 11 data fields, a total of 8 data fields met the acceptable accuracy standard, while another 3 data fields had an accuracy rate between 61.2% and 89.7%. Noticeably, the rule-based approach was shown to be more effective and robust in extracting variables of interest. On the other hand, ML/DL models had poorer predictive performances due to highly imbalanced data distribution and variable writing styles between different reports and data used for domain-specific pre-trained models. We designed an NLP algorithm that can automate clinical information extraction accurately from histopathology reports with an overall average micro accuracy of 93.3%.