Deep Learning Solutions for Classifying Patients on Opioid Use

Zhengping Che, Jennifer St. Sauver, Hongfang D Liu, Yan Liu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Opioid analgesics, as commonly prescribed medications used for relieving pain in patients, are especially prevalent in US these years. However, an increasing amount of opioid misuse and abuse have caused lots of consequences. Researchers and clinicians have attempted to discover the factors leading to opioid long-term use, dependence, and abuse, but only limited incidents are understood from previous works. Motivated by recent successes of deep learning and the abundant amount of electronic health records, we apply state-of-the-art deep and recurrent neural network models on a dataset of more than one hundred thousand opioid users. Our models are shown to achieve robust and superior results on classifying opioid users, and are able to extract key factors for different opioid user groups. This work is also a good demonstration on adopting novel deep learning methods for real-world health care problems.

Original languageEnglish (US)
Pages (from-to)525-534
Number of pages10
JournalAMIA ... Annual Symposium proceedings. AMIA Symposium
Volume2017
StatePublished - Jan 1 2017

Fingerprint

Opioid Analgesics
Learning
Neural Networks (Computer)
Electronic Health Records
Research Personnel
Delivery of Health Care
Pain

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Deep Learning Solutions for Classifying Patients on Opioid Use. / Che, Zhengping; St. Sauver, Jennifer; Liu, Hongfang D; Liu, Yan.

In: AMIA ... Annual Symposium proceedings. AMIA Symposium, Vol. 2017, 01.01.2017, p. 525-534.

Research output: Contribution to journalArticle

@article{fecd1a2cc049421faa00a8dd56f8f88c,
title = "Deep Learning Solutions for Classifying Patients on Opioid Use",
abstract = "Opioid analgesics, as commonly prescribed medications used for relieving pain in patients, are especially prevalent in US these years. However, an increasing amount of opioid misuse and abuse have caused lots of consequences. Researchers and clinicians have attempted to discover the factors leading to opioid long-term use, dependence, and abuse, but only limited incidents are understood from previous works. Motivated by recent successes of deep learning and the abundant amount of electronic health records, we apply state-of-the-art deep and recurrent neural network models on a dataset of more than one hundred thousand opioid users. Our models are shown to achieve robust and superior results on classifying opioid users, and are able to extract key factors for different opioid user groups. This work is also a good demonstration on adopting novel deep learning methods for real-world health care problems.",
author = "Zhengping Che and {St. Sauver}, Jennifer and Liu, {Hongfang D} and Yan Liu",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
volume = "2017",
pages = "525--534",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Deep Learning Solutions for Classifying Patients on Opioid Use

AU - Che, Zhengping

AU - St. Sauver, Jennifer

AU - Liu, Hongfang D

AU - Liu, Yan

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Opioid analgesics, as commonly prescribed medications used for relieving pain in patients, are especially prevalent in US these years. However, an increasing amount of opioid misuse and abuse have caused lots of consequences. Researchers and clinicians have attempted to discover the factors leading to opioid long-term use, dependence, and abuse, but only limited incidents are understood from previous works. Motivated by recent successes of deep learning and the abundant amount of electronic health records, we apply state-of-the-art deep and recurrent neural network models on a dataset of more than one hundred thousand opioid users. Our models are shown to achieve robust and superior results on classifying opioid users, and are able to extract key factors for different opioid user groups. This work is also a good demonstration on adopting novel deep learning methods for real-world health care problems.

AB - Opioid analgesics, as commonly prescribed medications used for relieving pain in patients, are especially prevalent in US these years. However, an increasing amount of opioid misuse and abuse have caused lots of consequences. Researchers and clinicians have attempted to discover the factors leading to opioid long-term use, dependence, and abuse, but only limited incidents are understood from previous works. Motivated by recent successes of deep learning and the abundant amount of electronic health records, we apply state-of-the-art deep and recurrent neural network models on a dataset of more than one hundred thousand opioid users. Our models are shown to achieve robust and superior results on classifying opioid users, and are able to extract key factors for different opioid user groups. This work is also a good demonstration on adopting novel deep learning methods for real-world health care problems.

UR - http://www.scopus.com/inward/record.url?scp=85057544915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057544915&partnerID=8YFLogxK

M3 - Article

C2 - 29854117

AN - SCOPUS:85057544915

VL - 2017

SP - 525

EP - 534

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

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

SN - 1559-4076

ER -