Skip to main content

Advertisement

Log in

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

  • Original Article
  • Published:
World Journal of Urology Aims and scope Submit manuscript

Abstract

Objective

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.

Materials and 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

Natural language processing 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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

Abbreviations

EMR:

Electronic medical records

NLP:

Natural language processing

ASAP:

Atypical small acinar proliferation

HGPIN:

High-grade intraepithelial neoplasia

TRUS:

Trans-rectal ultrasound

ICD:

International classification of diseases

References

  1. Jha AK et al (2009) Use of electronic health records in US hospitals. N Engl J Med 360(16):1628–1638

    Article  CAS  PubMed  Google Scholar 

  2. Blumenthal D (2010) Launching HITECH. N Engl J Med 362(5):382–385

    Article  CAS  PubMed  Google Scholar 

  3. Erickstad L et al (2011) Use of electronic medical records to identify patients at risk for prostate cancer in an academic institution. Prostate Cancer Prostatic Dis 14(1):85–89

    Article  CAS  PubMed  Google Scholar 

  4. Lau EC et al (2011) Use of electronic medical records (EMR) for oncology outcomes research: assessing the comparability of EMR information to patient registry and health claims data. Clin Epidemiol 3:259–272

    PubMed Central  PubMed  Google Scholar 

  5. Meystre SM et al. (2008) Extracting information from textual documents in the electronic health record: a review of recent research. Yearb Med Inform 1:128–44

    Google Scholar 

  6. Spyns P (1996) Natural language processing in medicine: an overview. Methods Inf Med 35(4–5):285–301

    CAS  PubMed  Google Scholar 

  7. Murff HJ et al (2011) Automated identification of postoperative complications within an electronic medical record using natural language processing. JAMA 306(8):848–855

    Article  CAS  PubMed  Google Scholar 

  8. Litwin MS, Saigal CS, Beerbohm EM (2005) The burden of urologic diseases in America. J Urol 173(4):1065–1066

    Article  PubMed  Google Scholar 

  9. Semins MJ, Trock BJ, Matlaga BR (2010) Validity of administrative coding in identifying patients with upper urinary tract calculi. J Urol 184(1):190–192

    Article  PubMed  Google Scholar 

  10. Kaafarani HM, Rosen AK (2009) Using administrative data to identify surgical adverse events: an introduction to the patient safety indicators. Am J Surg 198(5 Suppl):S63–S68

    Article  PubMed  Google Scholar 

  11. White RH et al (2009) How valid is the ICD-9-CM based AHRQ patient safety indicator for postoperative venous thromboembolism? Med Care 47(12):1237–1243

    Article  PubMed  Google Scholar 

  12. Ganeswaran D et al. (2012) Population-based linkage of health records to detect urological complications and hospitalisation following transrectal ultrasound-guided biopsies in men suspected of prostate cancer. World J Urol. doi:10.1007/s00345-012-0893-2

  13. Khwaja HA, Syed H, Cranston DW (2002) Coding errors: a comparative analysis of hospital and prospectively collected departmental data. BJU Int 89(3):178–180

    Article  CAS  PubMed  Google Scholar 

  14. Currie AM et al. (2006) Automated extraction of free-text from pathology reports. AMIA Annu Symp Proc 2006:899

Download references

Acknowledgments

Source of fund received from Intuitive Surgical.

Conflict of interest

None.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Anil A. Thomas.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Thomas, A.A., Zheng, C., Jung, H. et al. Extracting data from electronic medical records: validation of a natural language processing program to assess prostate biopsy results. World J Urol 32, 99–103 (2014). https://doi.org/10.1007/s00345-013-1040-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00345-013-1040-4

Keywords

Navigation