Abstract
With a paucity of pre-neoplastic lung models, identifying incidental pulmonary pre-neoplasia could provide tissue for molecular profiling and experiments to better understand carcinogenesis pathways. Ideally, these findings should be identifiable through manual or automated review of the pathology report texts. Natural language processing (NLP) is a digital method for analyzing and structuring free text, capable of parsing thousands of medical reports at once. Thus, we aim to utilize NLP to identify and extract preneoplastic pathological features from an initial pilot consisting of resected non-small cell lung cancer (NSCLC) patients, using unstructured pathology reports.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
