Needle in a Haystack: Natural Language Processing to Identify Serious Illness

Abstract

Background: Alone, administrative data poorly identifies patients with palliative care needs.

Objective: To identify patients with uncommon, yet devastating, illnesses using a combination of administrative data and natural language processing (NLP).

Design/setting: Retrospective cohort study using the electronic medical records of a healthcare network totaling over 2500 hospital beds. We sought to identify patient populations with two unique disease processes associated with a poor prognosis: pneumoperitoneum and leptomeningeal metastases from breast cancer.

Measurements: Patients with pneumoperitoneum or leptomeningeal metastasis from breast cancer were identified through administrative codes and NLP.

Results: Administrative codes alone resulted in identification of 6438 patients with possible pneumoperitoneum and 557 patients with possible leptomeningeal metastasis. Adding NLP to this analysis reduced the number of patients to 869 with pneumoperitoneum and 187 with leptomeningeal metastasis secondary to breast cancer. Administrative codes alone yielded a 13% positive predictive value (PPV) for pneumoperitoneum and 25% PPV for leptomeningeal metastasis. The combination of administrative codes and NLP achieved a PPV of 100%. The entire process was completed within hours.

Conclusions: Adding NLP to the use of administrative codes allows for rapid identification of seriously ill patients with otherwise difficult to detect disease processes and eliminates costly, tedious, and time-intensive manual chart review. This method enables studies to evaluate the effectiveness of treatment, including palliative interventions, for unique populations of seriously ill patients who cannot be identified by administrative codes alone.

Keywords: critical illness; natural language processing; patient identification.

FIG. 1.

Three stage process of patient identification.

FIG. 2.

Schematic of NLP. Sensitive, but nonspecific administrative codes are used to capture thousands of reports, which may be indicative of a disease process (A). NLP rapidly scans through the free-text reports and isolates those that screen positive for the desired search terms (B). In this example, the terms “free air” and “pneumoperitoneum” were used. Semiautomated review allows the researcher to review notes in which the search terms appear. The search terms are highlighted by the NLP to facilitate rapid review. If a note is confirmed positive, the reviewer can place an indicator in the annotated value box. In this case the reviewer used the digit “1” to indicate “free air.” The output from the screening is automatically exported to a spreadsheet (C). In this example, all data have been deidentified. CT, computed tomography; NLP, natural language processing.