Longitudinal analysis of pain in patients with metastatic prostate cancer using natural language processing of medical record text

Norris H. Heintzelman, Robert J. Taylor, Lone Simonsen, Roger Lustig, Doug Anderko, Jennifer Haythornthwaite, Lois C. Childs, George Steven Bova

Research output: Contribution to journalArticle

Abstract

Objectives: To test the feasibility of using text mining to depict meaningfully the experience of pain in patients with metastatic prostate cancer, to identify novel pain phenotypes, and to propose methods for longitudinal visualization of pain status. Materials and methods: Text from 4409 clinical encounters for 33 men enrolled in a 15-year longitudinal clinical/molecular autopsy study of metastatic prostate cancer (Project to ELIminate lethal CANcer) was subjected to natural language processing (NLP) using Unified Medical Language System-based terms. A four-tiered pain scale was developed, and logistic regression analysis identified factors that correlated with experience of severe pain during each month. Results: NLP identified 6387 pain and 13 827 drug mentions in the text. Graphical displays revealed the pain 'landscape' described in the textual records and confirmed dramatically increasing levels of pain in the last years of life in all but two patients, all of whom died from metastatic cancer. Severe pain was associated with receipt of opioids (OR=6.6, p

Original languageEnglish (US)
Pages (from-to)898-905
Number of pages8
JournalJournal of the American Medical Informatics Association
Volume20
Issue number5
DOIs
StatePublished - 2013

Fingerprint

Natural Language Processing
Medical Records
Prostatic Neoplasms
Pain
Unified Medical Language System
Data Mining
Opioid Analgesics
Autopsy
Neoplasms
Logistic Models
Regression Analysis
Phenotype

ASJC Scopus subject areas

  • Health Informatics

Cite this

Longitudinal analysis of pain in patients with metastatic prostate cancer using natural language processing of medical record text. / Heintzelman, Norris H.; Taylor, Robert J.; Simonsen, Lone; Lustig, Roger; Anderko, Doug; Haythornthwaite, Jennifer; Childs, Lois C.; Bova, George Steven.

In: Journal of the American Medical Informatics Association, Vol. 20, No. 5, 2013, p. 898-905.

Research output: Contribution to journalArticle

Heintzelman, Norris H. ; Taylor, Robert J. ; Simonsen, Lone ; Lustig, Roger ; Anderko, Doug ; Haythornthwaite, Jennifer ; Childs, Lois C. ; Bova, George Steven. / Longitudinal analysis of pain in patients with metastatic prostate cancer using natural language processing of medical record text. In: Journal of the American Medical Informatics Association. 2013 ; Vol. 20, No. 5. pp. 898-905.
@article{0cfd5d0fc48a49529baa439e3c67ec7c,
title = "Longitudinal analysis of pain in patients with metastatic prostate cancer using natural language processing of medical record text",
abstract = "Objectives: To test the feasibility of using text mining to depict meaningfully the experience of pain in patients with metastatic prostate cancer, to identify novel pain phenotypes, and to propose methods for longitudinal visualization of pain status. Materials and methods: Text from 4409 clinical encounters for 33 men enrolled in a 15-year longitudinal clinical/molecular autopsy study of metastatic prostate cancer (Project to ELIminate lethal CANcer) was subjected to natural language processing (NLP) using Unified Medical Language System-based terms. A four-tiered pain scale was developed, and logistic regression analysis identified factors that correlated with experience of severe pain during each month. Results: NLP identified 6387 pain and 13 827 drug mentions in the text. Graphical displays revealed the pain 'landscape' described in the textual records and confirmed dramatically increasing levels of pain in the last years of life in all but two patients, all of whom died from metastatic cancer. Severe pain was associated with receipt of opioids (OR=6.6, p",
author = "Heintzelman, {Norris H.} and Taylor, {Robert J.} and Lone Simonsen and Roger Lustig and Doug Anderko and Jennifer Haythornthwaite and Childs, {Lois C.} and Bova, {George Steven}",
year = "2013",
doi = "10.1136/amiajnl-2012-001076",
language = "English (US)",
volume = "20",
pages = "898--905",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "5",

}

TY - JOUR

T1 - Longitudinal analysis of pain in patients with metastatic prostate cancer using natural language processing of medical record text

AU - Heintzelman, Norris H.

AU - Taylor, Robert J.

AU - Simonsen, Lone

AU - Lustig, Roger

AU - Anderko, Doug

AU - Haythornthwaite, Jennifer

AU - Childs, Lois C.

AU - Bova, George Steven

PY - 2013

Y1 - 2013

N2 - Objectives: To test the feasibility of using text mining to depict meaningfully the experience of pain in patients with metastatic prostate cancer, to identify novel pain phenotypes, and to propose methods for longitudinal visualization of pain status. Materials and methods: Text from 4409 clinical encounters for 33 men enrolled in a 15-year longitudinal clinical/molecular autopsy study of metastatic prostate cancer (Project to ELIminate lethal CANcer) was subjected to natural language processing (NLP) using Unified Medical Language System-based terms. A four-tiered pain scale was developed, and logistic regression analysis identified factors that correlated with experience of severe pain during each month. Results: NLP identified 6387 pain and 13 827 drug mentions in the text. Graphical displays revealed the pain 'landscape' described in the textual records and confirmed dramatically increasing levels of pain in the last years of life in all but two patients, all of whom died from metastatic cancer. Severe pain was associated with receipt of opioids (OR=6.6, p

AB - Objectives: To test the feasibility of using text mining to depict meaningfully the experience of pain in patients with metastatic prostate cancer, to identify novel pain phenotypes, and to propose methods for longitudinal visualization of pain status. Materials and methods: Text from 4409 clinical encounters for 33 men enrolled in a 15-year longitudinal clinical/molecular autopsy study of metastatic prostate cancer (Project to ELIminate lethal CANcer) was subjected to natural language processing (NLP) using Unified Medical Language System-based terms. A four-tiered pain scale was developed, and logistic regression analysis identified factors that correlated with experience of severe pain during each month. Results: NLP identified 6387 pain and 13 827 drug mentions in the text. Graphical displays revealed the pain 'landscape' described in the textual records and confirmed dramatically increasing levels of pain in the last years of life in all but two patients, all of whom died from metastatic cancer. Severe pain was associated with receipt of opioids (OR=6.6, p

UR - http://www.scopus.com/inward/record.url?scp=84882760916&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882760916&partnerID=8YFLogxK

U2 - 10.1136/amiajnl-2012-001076

DO - 10.1136/amiajnl-2012-001076

M3 - Article

VL - 20

SP - 898

EP - 905

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 5

ER -