83 VALIDITY OF NATURAL LANGUAGE PROCESSING TO IDENTIFY PATIENTS WITH PROSTATE CANCER
Anil Thomas, Chengyi Zheng, Howard Jung, Allen Chang, Brian Kim, Joy S. Gelfond, Jeff M. Slezak, Kim Porter, Steven J. Jacobsen, Gary W. Chien · The Journal of Urology · 2013
You have accessJournal of UrologyGeneral & Epidemiological Trends & Socioeconomics: Evidence-Based Medicine & Outcomes (II)1 Apr 201383 VALIDITY OF NATURAL LANGUAGE PROCESSING TO IDENTIFY PATIENTS WITH PROSTATE CANCER Anil Thomas, Chengyi Zheng, Howard Jung, Allen Chang, Brian Kim, Joy Gelfond, Jeff Slezak, Kim Porter, Steven Jacobsen, and Gary Chien Anil ThomasAnil Thomas Los Angeles, CA , Chengyi ZhengChengyi Zheng Los Angeles, CA , Howard JungHoward Jung Los Angeles, CA , Allen ChangAllen Chang Los Angeles, CA , Brian KimBrian Kim Los Angeles, CA , Joy GelfondJoy Gelfond Los Angeles, CA , Jeff SlezakJeff Slezak Los Angeles, CA , Kim PorterKim Porter Los Angeles, CA , Steven JacobsenSteven Jacobsen Los Angeles, CA , and Gary ChienGary Chien Los Angeles, CA View All Author Informationhttps://doi.org/10.1016/j.juro.2013.02.1461AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookTwitterLinked InEmail INTRODUCTION AND OBJECTIVES The extraction of specific data from electronic medical records (EMR) remains tedious and is often performed manually. Natural language processing (NLP) programs have been developed to identify and extract information within clinical narrative text. We performed a study to assess the validity of an NLP program to accurately identify patients with prostate cancer and to retrieve pertinent pathologic information from their EMR. METHODS A retrospective review was performed of a prospectively collected database including patients from the Southern California Kaiser Permanente Medical Region that underwent prostate biopsies during a 2-week period. A NLP program was used to identify patients with prostate biopsies that were positive for prostatic adenocarcinoma from all pathology reports within this period. The application then processed 100 consecutive patients with prostate adenocarcinoma to extract 10 variables from their pathology reports. The extraction and retrieval of information by NLP was then compared to a blinded manual review. RESULTS A consecutive series of 18,453 pathology reports were evaluated. NLP correctly detected 117 out of 118 patients (99.1%) with prostatic adenocarcinoma after TRUS-guided prostate biopsy. NLP had a positive predictive value of 99.1% with a 99.1% sensitivity and a 99.9% specificity to correctly identify patients with prostatic adenocarcinoma after biopsy. The overall ability of the NLP application to accurately extract variables from the pathology reports was 97.6%. CONCLUSIONS NLP is a reliable and accurate method to identify select patients and to extract relevant data from an existing EMR in order to establish a prospective clinical database. © 2013 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 189Issue 4SApril 2013Page: e34 Advertisement Copyright & Permissions© 2013 by American Urological Association Education and Research, Inc.MetricsAuthor Information Anil Thomas Los Angeles, CA More articles by this author Chengyi Zheng Los Angeles, CA More articles by this author Howard Jung Los Angeles, CA More articles by this author Allen Chang Los Angeles, CA More articles by this author Brian Kim Los Angeles, CA More articles by this author Joy Gelfond Los Angeles, CA More articles by this author Jeff Slezak Los Angeles, CA More articles by this author Kim Porter Los Angeles, CA More articles by this author Steven Jacobsen Los Angeles, CA More articles by this author Gary Chien Los Angeles, CA More articles by this author Expand All Advertisement Advertisement PDF downloadLoading ...