Automated discovery of drug treatment patterns for endocrine therapy of breast cancer within an electronic medical record

Guergana K. Savova, Janet E Olson, Sean P. Murphy, Victoria L. Cafourek, Fergus J Couch, Matthew Philip Goetz, James N. Ingle, Vera Jean Suman, Christopher G. Chute, Richard M Weinshilboum

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Objective: To develop an algorithm for the discovery of drug treatment patterns for endocrine breast cancer therapy within an electronic medical record and to test the hypothesis that information extracted using it is comparable to the information found by traditional methods. Materials: The electronic medical charts of 1507 patients diagnosed with histologically confirmed primary invasive breast cancer. Methods: The automatic drug treatment classification tool consisted of components for: (1) extraction of drug treatment-relevant information from clinical narratives using natural language processing (clinical Text Analysis and Knowledge Extraction System); (2) extraction of drug treatment data from an electronic prescribing system; (3) merging information to create a patient treatment timeline; and (4) final classification logic. Results: Agreement between results from the algorithm and from a nurse abstractor is measured for categories: (0) no tamoxifen or aromatase inhibitor (AI) treatment; (1) tamoxifen only; (2) AI only; (3) tamoxifen before AI; (4) AI before tamoxifen; (5) multiple AIs and tamoxifen cycles in no specific order; and (6) no specific treatment dates. Specificity (all categories): 96.14%e100%; sensitivity (categories (0)-(4)): 90.27%-99.83%; sensitivity (categories (5)-(6)): 0-23.53%; positive predictive values: 80%e97.38%; negative predictive values: 96.91%e99.93%. Discussion: Our approach illustrates a secondary use of the electronic medical record. The main challenge is event temporality. Conclusion: We present an algorithm for automated treatment classification within an electronic medical record to combine information extracted through natural language processing with that extracted from structured databases. The algorithm has high specificity for all categories, high sensitivity for five categories, and low sensitivity for two categories.

Original languageEnglish (US)
JournalJournal of the American Medical Informatics Association
Volume19
Issue numberE1
DOIs
StatePublished - Jun 2012

Fingerprint

Electronic Health Records
Drug Discovery
Breast Neoplasms
Tamoxifen
Aromatase Inhibitors
Natural Language Processing
Therapeutics
Endocrine Gland Neoplasms
Electronic Prescribing
Medical Electronics
Pharmaceutical Preparations
Nurses
Databases

ASJC Scopus subject areas

  • Health Informatics

Cite this

Automated discovery of drug treatment patterns for endocrine therapy of breast cancer within an electronic medical record. / Savova, Guergana K.; Olson, Janet E; Murphy, Sean P.; Cafourek, Victoria L.; Couch, Fergus J; Goetz, Matthew Philip; Ingle, James N.; Suman, Vera Jean; Chute, Christopher G.; Weinshilboum, Richard M.

In: Journal of the American Medical Informatics Association, Vol. 19, No. E1, 06.2012.

Research output: Contribution to journalArticle

@article{ac331f8d689d46628860d86df83ad58e,
title = "Automated discovery of drug treatment patterns for endocrine therapy of breast cancer within an electronic medical record",
abstract = "Objective: To develop an algorithm for the discovery of drug treatment patterns for endocrine breast cancer therapy within an electronic medical record and to test the hypothesis that information extracted using it is comparable to the information found by traditional methods. Materials: The electronic medical charts of 1507 patients diagnosed with histologically confirmed primary invasive breast cancer. Methods: The automatic drug treatment classification tool consisted of components for: (1) extraction of drug treatment-relevant information from clinical narratives using natural language processing (clinical Text Analysis and Knowledge Extraction System); (2) extraction of drug treatment data from an electronic prescribing system; (3) merging information to create a patient treatment timeline; and (4) final classification logic. Results: Agreement between results from the algorithm and from a nurse abstractor is measured for categories: (0) no tamoxifen or aromatase inhibitor (AI) treatment; (1) tamoxifen only; (2) AI only; (3) tamoxifen before AI; (4) AI before tamoxifen; (5) multiple AIs and tamoxifen cycles in no specific order; and (6) no specific treatment dates. Specificity (all categories): 96.14{\%}e100{\%}; sensitivity (categories (0)-(4)): 90.27{\%}-99.83{\%}; sensitivity (categories (5)-(6)): 0-23.53{\%}; positive predictive values: 80{\%}e97.38{\%}; negative predictive values: 96.91{\%}e99.93{\%}. Discussion: Our approach illustrates a secondary use of the electronic medical record. The main challenge is event temporality. Conclusion: We present an algorithm for automated treatment classification within an electronic medical record to combine information extracted through natural language processing with that extracted from structured databases. The algorithm has high specificity for all categories, high sensitivity for five categories, and low sensitivity for two categories.",
author = "Savova, {Guergana K.} and Olson, {Janet E} and Murphy, {Sean P.} and Cafourek, {Victoria L.} and Couch, {Fergus J} and Goetz, {Matthew Philip} and Ingle, {James N.} and Suman, {Vera Jean} and Chute, {Christopher G.} and Weinshilboum, {Richard M}",
year = "2012",
month = "6",
doi = "10.1136/amiajnl-2011-000295",
language = "English (US)",
volume = "19",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "E1",

}

TY - JOUR

T1 - Automated discovery of drug treatment patterns for endocrine therapy of breast cancer within an electronic medical record

AU - Savova, Guergana K.

AU - Olson, Janet E

AU - Murphy, Sean P.

AU - Cafourek, Victoria L.

AU - Couch, Fergus J

AU - Goetz, Matthew Philip

AU - Ingle, James N.

AU - Suman, Vera Jean

AU - Chute, Christopher G.

AU - Weinshilboum, Richard M

PY - 2012/6

Y1 - 2012/6

N2 - Objective: To develop an algorithm for the discovery of drug treatment patterns for endocrine breast cancer therapy within an electronic medical record and to test the hypothesis that information extracted using it is comparable to the information found by traditional methods. Materials: The electronic medical charts of 1507 patients diagnosed with histologically confirmed primary invasive breast cancer. Methods: The automatic drug treatment classification tool consisted of components for: (1) extraction of drug treatment-relevant information from clinical narratives using natural language processing (clinical Text Analysis and Knowledge Extraction System); (2) extraction of drug treatment data from an electronic prescribing system; (3) merging information to create a patient treatment timeline; and (4) final classification logic. Results: Agreement between results from the algorithm and from a nurse abstractor is measured for categories: (0) no tamoxifen or aromatase inhibitor (AI) treatment; (1) tamoxifen only; (2) AI only; (3) tamoxifen before AI; (4) AI before tamoxifen; (5) multiple AIs and tamoxifen cycles in no specific order; and (6) no specific treatment dates. Specificity (all categories): 96.14%e100%; sensitivity (categories (0)-(4)): 90.27%-99.83%; sensitivity (categories (5)-(6)): 0-23.53%; positive predictive values: 80%e97.38%; negative predictive values: 96.91%e99.93%. Discussion: Our approach illustrates a secondary use of the electronic medical record. The main challenge is event temporality. Conclusion: We present an algorithm for automated treatment classification within an electronic medical record to combine information extracted through natural language processing with that extracted from structured databases. The algorithm has high specificity for all categories, high sensitivity for five categories, and low sensitivity for two categories.

AB - Objective: To develop an algorithm for the discovery of drug treatment patterns for endocrine breast cancer therapy within an electronic medical record and to test the hypothesis that information extracted using it is comparable to the information found by traditional methods. Materials: The electronic medical charts of 1507 patients diagnosed with histologically confirmed primary invasive breast cancer. Methods: The automatic drug treatment classification tool consisted of components for: (1) extraction of drug treatment-relevant information from clinical narratives using natural language processing (clinical Text Analysis and Knowledge Extraction System); (2) extraction of drug treatment data from an electronic prescribing system; (3) merging information to create a patient treatment timeline; and (4) final classification logic. Results: Agreement between results from the algorithm and from a nurse abstractor is measured for categories: (0) no tamoxifen or aromatase inhibitor (AI) treatment; (1) tamoxifen only; (2) AI only; (3) tamoxifen before AI; (4) AI before tamoxifen; (5) multiple AIs and tamoxifen cycles in no specific order; and (6) no specific treatment dates. Specificity (all categories): 96.14%e100%; sensitivity (categories (0)-(4)): 90.27%-99.83%; sensitivity (categories (5)-(6)): 0-23.53%; positive predictive values: 80%e97.38%; negative predictive values: 96.91%e99.93%. Discussion: Our approach illustrates a secondary use of the electronic medical record. The main challenge is event temporality. Conclusion: We present an algorithm for automated treatment classification within an electronic medical record to combine information extracted through natural language processing with that extracted from structured databases. The algorithm has high specificity for all categories, high sensitivity for five categories, and low sensitivity for two categories.

UR - http://www.scopus.com/inward/record.url?scp=84863538060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863538060&partnerID=8YFLogxK

U2 - 10.1136/amiajnl-2011-000295

DO - 10.1136/amiajnl-2011-000295

M3 - Article

C2 - 22140207

AN - SCOPUS:84863538060

VL - 19

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - E1

ER -