timimlerTimothy D. Imler Shares Key Findings from Research Published Online Early in the Red Journal, including why  natural language processing can play a vital role in colonoscopy quality measurement.



1. Explain natural language processing and its role in colonoscopy quality measurement/why it is important?

Natural language processing (NLP) is a computer-based technique for extracting meaningful information from text documents. This has been utilized since the 1950s for various purposes such as foreign language translation and winning Jeopardy competitions (Watson). More recently there has been an increasing focus on utilizing NLP within the medical field to extract information from clinical, radiological, and pathologic reports that previously required manual review. An example of this is with the extraction of adenoma detection rates (ADR) in colonoscopy. ADR has been shown to be a powerful predictor of quality for colonoscopy, however outside of trials this has been a challenge to report due to the time, expense, and potential abuse for reporting. NLP may allow the ability to eliminate manual review while maintaining high accuracy, even for more specialized quality measures for colonoscopy (e.g. advanced adenoma detection rate, sessile serrated polyp detection rate, number of adenomas per colonoscopy, and location specific detection rates).

  1. What’s new here and important for clinicians?

Clinicians must be aware of the challenges of accurately collecting and reporting quality measures for colonoscopy and how NLP technologies may allow for clinicians to focus on improvement in care, and not on how to collect the required information. This study shows the generalizability across the United States for this technology regardless of the source of creation of the colonoscopy report.

  1. What do patients need to know?

Patients need to know that NLP will potentially be a means for publically reporting quality measurements on individual endoscopists and allow for patient selection of provider based on quality.

  1. If you could predict the future, how do you see natural language processing changing healthcare, and the practice of gastroenterology?

Natural language processing for colonoscopy has a bright future for both clinicians and the patients we serve. The optimal utilization within colonoscopy would be to have a procedure performed, pathology potentially generated, NLP of the procedure and pathologic records, automated reporting to the provider/patient/primary care/quality reporting agency (GIQuIC)/payer for quality measures, and generation of a guideline appropriate surveillance interval. While we must individualize patient care, NLP will allow for a glimpse into the practice patterns of individuals and potentially allow for a means for intervention to improve care.

About Dr. Imler

Dr. Imler is a Regenstrief Institute investigator and assistant professor of medicine in the division of gastroenterology and hepatology at Indiana University School of Medicine.

Access the full article in the Advanced Online Publication (March 10, 2015) section of The American Journal of Gastroenterology website.

Recent Media Coverage

Healio Gastroenterology, March 10, 2015