Novel use of natural language processing for registry development in peritoneal surface malignancies

Traditional methods of research registry development for rare conditions such as peritoneal surface malignancies (PSM) are often hindered by poor patient accrual and need for significant manpower resources. We develop a novel pipeline using natural language processing (NLP) to accelerate this process and demonstrate its real-world application in the identification of PSM patients, as well as characterisation of referral patterns in this cohort. A training set comprising 100 radiological reports of abdomen and pelvis computed tomography scans was used to develop a rule-based NLP system able to classify reports based on the presence or absence of PSM. The algorithm was applied to a test set of 10,261 reports to identify all patients with PSM for registry creation. The registry was subsequently linked to electronic medical records, and the referral patterns of patients evaluated. The algorithm identified 251 reports as positive for PSM from a total of 10,261 reports, of which 239 were concordant with manual review. Performance was excellent with a specificity of 90%, positive predictive value of 95%, and accuracy of 96%. From these, 228 unique patients were identified for registry inclusion after corroboration with pathological findings. Only 27.6% of patients were found to have been referred to and reviewed by PSM specialist surgeons. For those without a PSM specialist consult, 39.4% were managed by medical oncology, 11.5% by colorectal surgery, 7.3% by gastroenterology, 5.4% by internal medicine, and 29.1% by various other miscellaneous medical and surgical subspecialties. NLP is a useful tool in automated pipelines that can greatly contribute to registry creation, as well as research and quality improvement efforts.