Comparing methods for identifying pancreatic cancer patients using electronic data sources

Jeff Friedlin, Marc Overhage, Mohammed A. Al-Haddad, Joshua A. Waters, J. Juan R Aguilar-Saavedra, Joe Kesterson, C. Schmidt

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

We sought to determine the accuracy of two electronic methods of identifying pancreatic cancer in a cohort of pancreatic cyst patients, and to examine the reasons for identification failure. We used the International Classification of Diseases, 9(th) Edition (ICD-9) codes and natural language processing (NLP) technology to identify pancreatic cancer in these patients. We compared both methods to a human-validated gold-standard surgical database. Both ICD-9 codes and NLP technology achieved high sensitivity for identifying pancreatic cancer, but the ICD-9 code method achieved markedly lower specificity and PPV compared to the NLP method. The NLP method required only slightly greater expenditures of time and effort compared to the ICD-9 code method. We identified several variables influencing the accuracy of ICD-9 codes to identify cancer patients including: the identification algorithm, kind of cancer to be identified, presence of other conditions similar to cancer, and presence of conditions that are precancerous.

Original languageEnglish (US)
Pages (from-to)237-241
Number of pages5
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
Volume2010
StatePublished - 2010

Fingerprint

Information Storage and Retrieval
International Classification of Diseases
Pancreatic Neoplasms
Natural Language Processing
Precancerous Conditions
Pancreatic Cyst
Technology
Neoplasms
Health Expenditures
Gold
Databases

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Friedlin, J., Overhage, M., Al-Haddad, M. A., Waters, J. A., Aguilar-Saavedra, J. J. R., Kesterson, J., & Schmidt, C. (2010). Comparing methods for identifying pancreatic cancer patients using electronic data sources. AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2010, 237-241.

Comparing methods for identifying pancreatic cancer patients using electronic data sources. / Friedlin, Jeff; Overhage, Marc; Al-Haddad, Mohammed A.; Waters, Joshua A.; Aguilar-Saavedra, J. Juan R; Kesterson, Joe; Schmidt, C.

In: AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, Vol. 2010, 2010, p. 237-241.

Research output: Contribution to journalArticle

Friedlin, J, Overhage, M, Al-Haddad, MA, Waters, JA, Aguilar-Saavedra, JJR, Kesterson, J & Schmidt, C 2010, 'Comparing methods for identifying pancreatic cancer patients using electronic data sources', AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, vol. 2010, pp. 237-241.
Friedlin J, Overhage M, Al-Haddad MA, Waters JA, Aguilar-Saavedra JJR, Kesterson J et al. Comparing methods for identifying pancreatic cancer patients using electronic data sources. AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium. 2010;2010:237-241.
Friedlin, Jeff ; Overhage, Marc ; Al-Haddad, Mohammed A. ; Waters, Joshua A. ; Aguilar-Saavedra, J. Juan R ; Kesterson, Joe ; Schmidt, C. / Comparing methods for identifying pancreatic cancer patients using electronic data sources. In: AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium. 2010 ; Vol. 2010. pp. 237-241.
@article{94b6fa8826904f538880a0333f2aa43e,
title = "Comparing methods for identifying pancreatic cancer patients using electronic data sources",
abstract = "We sought to determine the accuracy of two electronic methods of identifying pancreatic cancer in a cohort of pancreatic cyst patients, and to examine the reasons for identification failure. We used the International Classification of Diseases, 9(th) Edition (ICD-9) codes and natural language processing (NLP) technology to identify pancreatic cancer in these patients. We compared both methods to a human-validated gold-standard surgical database. Both ICD-9 codes and NLP technology achieved high sensitivity for identifying pancreatic cancer, but the ICD-9 code method achieved markedly lower specificity and PPV compared to the NLP method. The NLP method required only slightly greater expenditures of time and effort compared to the ICD-9 code method. We identified several variables influencing the accuracy of ICD-9 codes to identify cancer patients including: the identification algorithm, kind of cancer to be identified, presence of other conditions similar to cancer, and presence of conditions that are precancerous.",
author = "Jeff Friedlin and Marc Overhage and Al-Haddad, {Mohammed A.} and Waters, {Joshua A.} and Aguilar-Saavedra, {J. Juan R} and Joe Kesterson and C. Schmidt",
year = "2010",
language = "English (US)",
volume = "2010",
pages = "237--241",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Comparing methods for identifying pancreatic cancer patients using electronic data sources

AU - Friedlin, Jeff

AU - Overhage, Marc

AU - Al-Haddad, Mohammed A.

AU - Waters, Joshua A.

AU - Aguilar-Saavedra, J. Juan R

AU - Kesterson, Joe

AU - Schmidt, C.

PY - 2010

Y1 - 2010

N2 - We sought to determine the accuracy of two electronic methods of identifying pancreatic cancer in a cohort of pancreatic cyst patients, and to examine the reasons for identification failure. We used the International Classification of Diseases, 9(th) Edition (ICD-9) codes and natural language processing (NLP) technology to identify pancreatic cancer in these patients. We compared both methods to a human-validated gold-standard surgical database. Both ICD-9 codes and NLP technology achieved high sensitivity for identifying pancreatic cancer, but the ICD-9 code method achieved markedly lower specificity and PPV compared to the NLP method. The NLP method required only slightly greater expenditures of time and effort compared to the ICD-9 code method. We identified several variables influencing the accuracy of ICD-9 codes to identify cancer patients including: the identification algorithm, kind of cancer to be identified, presence of other conditions similar to cancer, and presence of conditions that are precancerous.

AB - We sought to determine the accuracy of two electronic methods of identifying pancreatic cancer in a cohort of pancreatic cyst patients, and to examine the reasons for identification failure. We used the International Classification of Diseases, 9(th) Edition (ICD-9) codes and natural language processing (NLP) technology to identify pancreatic cancer in these patients. We compared both methods to a human-validated gold-standard surgical database. Both ICD-9 codes and NLP technology achieved high sensitivity for identifying pancreatic cancer, but the ICD-9 code method achieved markedly lower specificity and PPV compared to the NLP method. The NLP method required only slightly greater expenditures of time and effort compared to the ICD-9 code method. We identified several variables influencing the accuracy of ICD-9 codes to identify cancer patients including: the identification algorithm, kind of cancer to be identified, presence of other conditions similar to cancer, and presence of conditions that are precancerous.

UR - http://www.scopus.com/inward/record.url?scp=84964959539&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964959539&partnerID=8YFLogxK

M3 - Article

VL - 2010

SP - 237

EP - 241

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -