Background: Nursing navigators spend up to 50% of their time identifying cancer patients. Timeliness to care is important to cancer patients early in their diagnosis. Manual identification of cancer patients in an EMR system is time consuming and not standardized.
Objective: Create a standardized method using technology (software) to identify cancer patients at the point of diagnosis for potential navigation.
Methods: In collaboration with Nursing and Information Technology, Natural Language Processing (NLP) software was designed to analyze content from EMR pathology reports. Predesignated key terms such as histology types are paired with tumor site-specific key terms such as anatomical sites or name of disease. The report is then sent in an automated fashion to our navigators within 24 hours. Once navigation is accepted by the ordering physician and the patient, the navigator ensures the patient is treated utilizing a specific clinical coordination standardized pathway.
Results: The pilot lasted 10 weeks and included thoracic and complex GI tumor site cases. Just under 1300 thoracic and complex GI cancer cases were automatically identified by NLP software from our Sarah Cannon community-based centers. A total of 894 patients were navigated during the pilot, with 414 of those patients identified using NLP software. Comparatively, in the previous year (for the same 10-week period), a total of 469 patients were navigated (using manual attrition only). The difference is a 91% increase in the number of patients navigated from the previous year.
Conclusions: Timely access to navigators is of utmost importance to cancer patients. The use of NLP to identify positive cancer patients at the point of diagnosis creates a standardized method for navigators to receive patients. Utilizing technology to help identify patients allows more time for navigators to assist patients early in their care as well as spending more valuable time with patients.
Implications: This pilot study is expanding to include multiple institutions within the Sarah Cannon network. Standardization also allows Sarah Cannon to look at patient retention and incremental value over time.
Limitations: It is not known if the increased number of patients was specifically related to the addition of NLP. Other possible contributory factors could be related to market growth, navigator reach, program advancement, marketing, etc.