Automated pancreatic cyst screening using natural language processing: A new tool in the early detection of pancreatic cancer

Alexandra M. Roch, Saeed Mehrabi, Anand Krishnan, Heidi E. Schmidt, Joseph Kesterson, Chris Beesley, Paul R. Dexter, Mathew Palakal, C. Max Schmidt

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Introduction As many as 3% of computed tomography (CT) scans detect pancreatic cysts. Because pancreatic cysts are incidental, ubiquitous and poorly understood, follow-up is often not performed. Pancreatic cysts may have a significant malignant potential and their identification represents a 'window of opportunity' for the early detection of pancreatic cancer. The purpose of this study was to implement an automated Natural Language Processing (NLP)-based pancreatic cyst identification system. Method A multidisciplinary team was assembled. NLP-based identification algorithms were developed based on key words commonly used by physicians to describe pancreatic cysts and programmed for automated search of electronic medical records. A pilot study was conducted prospectively in a single institution. Results From March to September 2013, 566 233 reports belonging to 50 669 patients were analysed. The mean number of patients reported with a pancreatic cyst was 88/month (range 78-98). The mean sensitivity and specificity were 99.9% and 98.8%, respectively. Conclusion NLP is an effective tool to automatically identify patients with pancreatic cysts based on electronic medical records (EMR). This highly accurate system can help capture patients 'at-risk' of pancreatic cancer in a registry.

Original languageEnglish (US)
Pages (from-to)447-453
Number of pages7
JournalHPB
Volume17
Issue number5
DOIs
StatePublished - May 1 2015

Fingerprint

Natural Language Processing
Pancreatic Cyst
Pancreatic Neoplasms
Early Detection of Cancer
Electronic Health Records
Registries
Tomography
Physicians
Sensitivity and Specificity

ASJC Scopus subject areas

  • Hepatology
  • Gastroenterology

Cite this

Automated pancreatic cyst screening using natural language processing : A new tool in the early detection of pancreatic cancer. / Roch, Alexandra M.; Mehrabi, Saeed; Krishnan, Anand; Schmidt, Heidi E.; Kesterson, Joseph; Beesley, Chris; Dexter, Paul R.; Palakal, Mathew; Schmidt, C. Max.

In: HPB, Vol. 17, No. 5, 01.05.2015, p. 447-453.

Research output: Contribution to journalArticle

Roch, AM, Mehrabi, S, Krishnan, A, Schmidt, HE, Kesterson, J, Beesley, C, Dexter, PR, Palakal, M & Schmidt, CM 2015, 'Automated pancreatic cyst screening using natural language processing: A new tool in the early detection of pancreatic cancer', HPB, vol. 17, no. 5, pp. 447-453. https://doi.org/10.1111/hpb.12375
Roch, Alexandra M. ; Mehrabi, Saeed ; Krishnan, Anand ; Schmidt, Heidi E. ; Kesterson, Joseph ; Beesley, Chris ; Dexter, Paul R. ; Palakal, Mathew ; Schmidt, C. Max. / Automated pancreatic cyst screening using natural language processing : A new tool in the early detection of pancreatic cancer. In: HPB. 2015 ; Vol. 17, No. 5. pp. 447-453.
@article{e94f720f23544ac9b789831c65166144,
title = "Automated pancreatic cyst screening using natural language processing: A new tool in the early detection of pancreatic cancer",
abstract = "Introduction As many as 3{\%} of computed tomography (CT) scans detect pancreatic cysts. Because pancreatic cysts are incidental, ubiquitous and poorly understood, follow-up is often not performed. Pancreatic cysts may have a significant malignant potential and their identification represents a 'window of opportunity' for the early detection of pancreatic cancer. The purpose of this study was to implement an automated Natural Language Processing (NLP)-based pancreatic cyst identification system. Method A multidisciplinary team was assembled. NLP-based identification algorithms were developed based on key words commonly used by physicians to describe pancreatic cysts and programmed for automated search of electronic medical records. A pilot study was conducted prospectively in a single institution. Results From March to September 2013, 566 233 reports belonging to 50 669 patients were analysed. The mean number of patients reported with a pancreatic cyst was 88/month (range 78-98). The mean sensitivity and specificity were 99.9{\%} and 98.8{\%}, respectively. Conclusion NLP is an effective tool to automatically identify patients with pancreatic cysts based on electronic medical records (EMR). This highly accurate system can help capture patients 'at-risk' of pancreatic cancer in a registry.",
author = "Roch, {Alexandra M.} and Saeed Mehrabi and Anand Krishnan and Schmidt, {Heidi E.} and Joseph Kesterson and Chris Beesley and Dexter, {Paul R.} and Mathew Palakal and Schmidt, {C. Max}",
year = "2015",
month = "5",
day = "1",
doi = "10.1111/hpb.12375",
language = "English (US)",
volume = "17",
pages = "447--453",
journal = "HPB",
issn = "1365-182X",
publisher = "John Wiley and Sons Inc.",
number = "5",

}

TY - JOUR

T1 - Automated pancreatic cyst screening using natural language processing

T2 - A new tool in the early detection of pancreatic cancer

AU - Roch, Alexandra M.

AU - Mehrabi, Saeed

AU - Krishnan, Anand

AU - Schmidt, Heidi E.

AU - Kesterson, Joseph

AU - Beesley, Chris

AU - Dexter, Paul R.

AU - Palakal, Mathew

AU - Schmidt, C. Max

PY - 2015/5/1

Y1 - 2015/5/1

N2 - Introduction As many as 3% of computed tomography (CT) scans detect pancreatic cysts. Because pancreatic cysts are incidental, ubiquitous and poorly understood, follow-up is often not performed. Pancreatic cysts may have a significant malignant potential and their identification represents a 'window of opportunity' for the early detection of pancreatic cancer. The purpose of this study was to implement an automated Natural Language Processing (NLP)-based pancreatic cyst identification system. Method A multidisciplinary team was assembled. NLP-based identification algorithms were developed based on key words commonly used by physicians to describe pancreatic cysts and programmed for automated search of electronic medical records. A pilot study was conducted prospectively in a single institution. Results From March to September 2013, 566 233 reports belonging to 50 669 patients were analysed. The mean number of patients reported with a pancreatic cyst was 88/month (range 78-98). The mean sensitivity and specificity were 99.9% and 98.8%, respectively. Conclusion NLP is an effective tool to automatically identify patients with pancreatic cysts based on electronic medical records (EMR). This highly accurate system can help capture patients 'at-risk' of pancreatic cancer in a registry.

AB - Introduction As many as 3% of computed tomography (CT) scans detect pancreatic cysts. Because pancreatic cysts are incidental, ubiquitous and poorly understood, follow-up is often not performed. Pancreatic cysts may have a significant malignant potential and their identification represents a 'window of opportunity' for the early detection of pancreatic cancer. The purpose of this study was to implement an automated Natural Language Processing (NLP)-based pancreatic cyst identification system. Method A multidisciplinary team was assembled. NLP-based identification algorithms were developed based on key words commonly used by physicians to describe pancreatic cysts and programmed for automated search of electronic medical records. A pilot study was conducted prospectively in a single institution. Results From March to September 2013, 566 233 reports belonging to 50 669 patients were analysed. The mean number of patients reported with a pancreatic cyst was 88/month (range 78-98). The mean sensitivity and specificity were 99.9% and 98.8%, respectively. Conclusion NLP is an effective tool to automatically identify patients with pancreatic cysts based on electronic medical records (EMR). This highly accurate system can help capture patients 'at-risk' of pancreatic cancer in a registry.

UR - http://www.scopus.com/inward/record.url?scp=84927509831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927509831&partnerID=8YFLogxK

U2 - 10.1111/hpb.12375

DO - 10.1111/hpb.12375

M3 - Article

C2 - 25537257

AN - SCOPUS:84927509831

VL - 17

SP - 447

EP - 453

JO - HPB

JF - HPB

SN - 1365-182X

IS - 5

ER -