• Charlotta Lindvall, Elizabeth J Lilley, Sophia N Zupanc, Isabel Chien, Brooks V Udelsman, Anne Walling, Zara Cooper, and James A Tulsky.
• 1 Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, Massachusetts.
• J Palliat Med. 2019 Feb 1; 22 (2): 183-187.

BackgroundPalliative surgical procedures are frequently performed to reduce symptoms in patients with advanced cancer, but quality is difficult to measure.ObjectiveTo determine whether natural language processing (NLP) of the electronic health record (EHR) can be used to (1) identify a population of cancer patients receiving palliative gastrostomy and (2) assess documentation of end-of-life process measures in the EHR.Design/SettingRetrospective cohort study of 302 adult cancer patients who received a gastrostomy tube at a single tertiary medical center.MeasurementsSensitivity and specificity of NLP compared to gold standard of manual chart abstraction in identifying a palliative indication for gastrostomy tube placement and documentation of goals of care discussions, code status determination, palliative care referral, and hospice assessment.ResultsAmong 302 cancer patients who underwent gastrostomy, 68 (22.5%) were classified by NLP as having a palliative indication for the procedure compared to 71 patients (23.5%) classified by human coders. Human chart abstraction took >2600 times longer than NLP (28 hours vs. 38 seconds). NLP identified the correct patients with 95.8% sensitivity and 97.4% specificity. NLP also identified end-of-life process measures with high sensitivity (85.7%-92.9%,) and specificity (96.7%-98.9%). In the two months leading up to palliative gastrostomy placement, 20.5% of patients had goals of care discussions documented. During the index hospitalization, 67.7% had goals of care discussions documented.ConclusionsNLP offers opportunities to identify patients receiving palliative surgical procedures and can rapidly assess established end-of-life process measures with an accuracy approaching that of human coders.

23 keywords...

hide…