Schroeck FR, et al. - Researchers established and validated a natural language processing (NLP) engine that abstracts pathology data from full text pathology reports to take a first step towards assembling population based cohorts of bladder cancer patients with longitudinal pathology data. The data showee that natural language processing had high accuracy for five of six variables and abstracted data for the vast majority of patients. In addition, this now allows for assembly of population based cohorts with longitudinal pathology data.