Extracting data from electronic medical records: Validation of a natural language processing program to assess prostate biopsy results, "Beyond the Abstract," by Anil A. Thomas, MD and Gary W. Chien, MD

BERKELEY, CA (UroToday.com) - Our study investigates the application and validation of a natural language processing (NLP) system, in a clinical context, to assess patients undergoing prostate biopsies. The widespread adoption of electronic medical records has greatly improved the efficiency and safety of health care delivery. However, the extraction of collected data for the purposes of quality analysis and research outcomes remains tedious and is often performed manually. NLP programs have been developed to identify and extract information within clinical narrative text. Furthermore there is a paucity of research on the application of NLP systems in clinical medicine, especially within the field of urology. Our study assesses the validity of an NLP program to accurately identify patients with prostate cancer and to retrieve pertinent pathologic information from their electronic medical records.

We feel that our findings are of utmost importance to clinicians. At present, little is known regarding the integration of bioinformatics with programs such as NLP in the clinical arena. Currently we are all spending too much time, effort, and money to manually acquire clinically meaningful data from patient records. In the future, programs such as NLP will automate what is currently being performed manually, thus saving a tremendous amount of time and money, as well as bringing about a reduction in human error. In our study we illustrate a poignant example of implementation of such a program in order to establish a prostate cancer database. We are now using this database to assess quality-of-life factors after treatment for prostate cancer. Importantly we have validated this automated tool to demonstrate high accuracy, sensitivity, and specificity to identify patients with prostate cancer.

 

Written by:
Anil A. Thomas, MD and Gary W. Chien, MD as part of Beyond the Abstract on UroToday.com. This initiative offers a method of publishing for the professional urology community. Authors are given an opportunity to expand on the circumstances, limitations etc... of their research by referencing the published abstract.

Department of Urology, Los Angeles Medical Center, Kaiser Permanente, 4900 Sunset Boulevard, Los Angeles, CA USA

Extracting data from electronic medical records: Validation of a natural language processing program to assess prostate biopsy results - Abstract

More Information about Beyond the Abstract