Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors

T. Elizabeth Workman; Qing Zeng-Treitler; Yijun Shao; Joel Kupersmith; Friedhelm Sandbrink; Joseph L. Goulet; Nawar M. Shaar; Christopher Spevak; Cynthia Brandt; Marc R. Blackman

doi:10.1109/BigData47090.2019.9006297

Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors

T. Elizabeth Workman, Qing Zeng-Treitler, Yijun Shao, Joel Kupersmith, Friedhelm Sandbrink, Joseph L. Goulet, Nawar M. Shaar, Christopher Spevak, Cynthia Brandt, Marc R. Blackman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Opioid Use Disorder is an international crisis, affecting many populations. Deep learning models can potentially predict opioid use disorder, but provide little insight to how predictions are derived. Impact scores, a new development in explainable artificial intelligence, measure how individual features affect deep learning outcomes. We modeled clinical visits to predict opioid use disorder, computed impact scores, and compared them to odds log ratios from logistic regression. Impact scores were generally comparable to odds log ratios, in providing insight to opioid abuse risk, but from a better-performing method than logistic regression.

Original language	English (US)
Title of host publication	Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019
Editors	Chaitanya Baru, Jun Huan, Latifur Khan, Xiaohua Tony Hu, Ronay Ak, Yuanyuan Tian, Roger Barga, Carlo Zaniolo, Kisung Lee, Yanfang Fanny Ye
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4883-4888
Number of pages	6
ISBN (Electronic)	9781728108582
DOIs	https://doi.org/10.1109/BigData47090.2019.9006297
State	Published - Dec 2019
Externally published	Yes
Event	2019 IEEE International Conference on Big Data, Big Data 2019 - Los Angeles, United States Duration: Dec 9 2019 → Dec 12 2019

Publication series

Name	Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019

Conference

Conference	2019 IEEE International Conference on Big Data, Big Data 2019
Country/Territory	United States
City	Los Angeles
Period	12/9/19 → 12/12/19

Keywords

Deep Learning
Explainable AI
Impact Scores
Opioid Use Disorder

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems
Information Systems and Management

Access to Document

10.1109/BigData47090.2019.9006297

Cite this

Workman, T. E., Zeng-Treitler, Q., Shao, Y., Kupersmith, J., Sandbrink, F., Goulet, J. L., Shaar, N. M., Spevak, C., Brandt, C., & Blackman, M. R. (2019). Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors. In C. Baru, J. Huan, L. Khan, X. T. Hu, R. Ak, Y. Tian, R. Barga, C. Zaniolo, K. Lee, & Y. F. Ye (Eds.), Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019 (pp. 4883-4888). [9006297] (Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigData47090.2019.9006297

Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors. / Workman, T. Elizabeth; Zeng-Treitler, Qing; Shao, Yijun et al.
Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019. ed. / Chaitanya Baru; Jun Huan; Latifur Khan; Xiaohua Tony Hu; Ronay Ak; Yuanyuan Tian; Roger Barga; Carlo Zaniolo; Kisung Lee; Yanfang Fanny Ye. Institute of Electrical and Electronics Engineers Inc., 2019. p. 4883-4888 9006297 (Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Workman, TE, Zeng-Treitler, Q, Shao, Y, Kupersmith, J, Sandbrink, F, Goulet, JL, Shaar, NM, Spevak, C, Brandt, C & Blackman, MR 2019, Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors. in C Baru, J Huan, L Khan, XT Hu, R Ak, Y Tian, R Barga, C Zaniolo, K Lee & YF Ye (eds), Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019., 9006297, Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019, Institute of Electrical and Electronics Engineers Inc., pp. 4883-4888, 2019 IEEE International Conference on Big Data, Big Data 2019, Los Angeles, United States, 12/9/19. https://doi.org/10.1109/BigData47090.2019.9006297

Workman TE, Zeng-Treitler Q, Shao Y, Kupersmith J, Sandbrink F, Goulet JL et al. Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors. In Baru C, Huan J, Khan L, Hu XT, Ak R, Tian Y, Barga R, Zaniolo C, Lee K, Ye YF, editors, Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 4883-4888. 9006297. (Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019). doi: 10.1109/BigData47090.2019.9006297

Workman, T. Elizabeth ; Zeng-Treitler, Qing ; Shao, Yijun et al. / Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors. Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019. editor / Chaitanya Baru ; Jun Huan ; Latifur Khan ; Xiaohua Tony Hu ; Ronay Ak ; Yuanyuan Tian ; Roger Barga ; Carlo Zaniolo ; Kisung Lee ; Yanfang Fanny Ye. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 4883-4888 (Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019).

@inproceedings{15385eb41215430795d5a23cccbdafae,

title = "Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors",

abstract = "Opioid Use Disorder is an international crisis, affecting many populations. Deep learning models can potentially predict opioid use disorder, but provide little insight to how predictions are derived. Impact scores, a new development in explainable artificial intelligence, measure how individual features affect deep learning outcomes. We modeled clinical visits to predict opioid use disorder, computed impact scores, and compared them to odds log ratios from logistic regression. Impact scores were generally comparable to odds log ratios, in providing insight to opioid abuse risk, but from a better-performing method than logistic regression.",

keywords = "Deep Learning, Explainable AI, Impact Scores, Opioid Use Disorder",

author = "Workman, {T. Elizabeth} and Qing Zeng-Treitler and Yijun Shao and Joel Kupersmith and Friedhelm Sandbrink and Goulet, {Joseph L.} and Shaar, {Nawar M.} and Christopher Spevak and Cynthia Brandt and Blackman, {Marc R.}",

note = "Funding Information: ACKNOWLEDGMENT The views expressed are those of the authors and do not necessarily reflect those of the Department of Veterans Affairs, the United States Government, or the academic affiliate organizations. This work was supported by VA Project SIP 18-329 Utilization of Opioids in Post 9/11 Veterans in the VA Community, and NIH grants UL1TR001876 and KL2TR001877 from the National Center for Advancing Translational Sciences. Funding Information: Funding for this research was provided in whole or in part by VHA project SIP 18–329, and NIH grants UL1TR001876 and KL2TR001877 from the National Center for Advancing Translational Sciences. XXX-X-XXXX-XXXX-X/XX/$XX.00 {\textcopyright}20XX IEEE Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference on Big Data, Big Data 2019 ; Conference date: 09-12-2019 Through 12-12-2019",

year = "2019",

month = dec,

doi = "10.1109/BigData47090.2019.9006297",

language = "English (US)",

series = "Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4883--4888",

editor = "Chaitanya Baru and Jun Huan and Latifur Khan and Hu, {Xiaohua Tony} and Ronay Ak and Yuanyuan Tian and Roger Barga and Carlo Zaniolo and Kisung Lee and Ye, {Yanfang Fanny}",

booktitle = "Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019",

}

TY - GEN

T1 - Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors

AU - Workman, T. Elizabeth

AU - Zeng-Treitler, Qing

AU - Shao, Yijun

AU - Kupersmith, Joel

AU - Sandbrink, Friedhelm

AU - Goulet, Joseph L.

AU - Shaar, Nawar M.

AU - Spevak, Christopher

AU - Brandt, Cynthia

AU - Blackman, Marc R.

N1 - Funding Information: ACKNOWLEDGMENT The views expressed are those of the authors and do not necessarily reflect those of the Department of Veterans Affairs, the United States Government, or the academic affiliate organizations. This work was supported by VA Project SIP 18-329 Utilization of Opioids in Post 9/11 Veterans in the VA Community, and NIH grants UL1TR001876 and KL2TR001877 from the National Center for Advancing Translational Sciences. Funding Information: Funding for this research was provided in whole or in part by VHA project SIP 18–329, and NIH grants UL1TR001876 and KL2TR001877 from the National Center for Advancing Translational Sciences. XXX-X-XXXX-XXXX-X/XX/$XX.00 ©20XX IEEE Publisher Copyright: © 2019 IEEE.

PY - 2019/12

Y1 - 2019/12

N2 - Opioid Use Disorder is an international crisis, affecting many populations. Deep learning models can potentially predict opioid use disorder, but provide little insight to how predictions are derived. Impact scores, a new development in explainable artificial intelligence, measure how individual features affect deep learning outcomes. We modeled clinical visits to predict opioid use disorder, computed impact scores, and compared them to odds log ratios from logistic regression. Impact scores were generally comparable to odds log ratios, in providing insight to opioid abuse risk, but from a better-performing method than logistic regression.

AB - Opioid Use Disorder is an international crisis, affecting many populations. Deep learning models can potentially predict opioid use disorder, but provide little insight to how predictions are derived. Impact scores, a new development in explainable artificial intelligence, measure how individual features affect deep learning outcomes. We modeled clinical visits to predict opioid use disorder, computed impact scores, and compared them to odds log ratios from logistic regression. Impact scores were generally comparable to odds log ratios, in providing insight to opioid abuse risk, but from a better-performing method than logistic regression.

KW - Deep Learning

KW - Explainable AI

KW - Impact Scores

KW - Opioid Use Disorder

UR - http://www.scopus.com/inward/record.url?scp=85081390455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85081390455&partnerID=8YFLogxK

U2 - 10.1109/BigData47090.2019.9006297

DO - 10.1109/BigData47090.2019.9006297

M3 - Conference contribution

AN - SCOPUS:85081390455

T3 - Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019

SP - 4883

EP - 4888

BT - Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019

A2 - Baru, Chaitanya

A2 - Huan, Jun

A2 - Khan, Latifur

A2 - Hu, Xiaohua Tony

A2 - Ak, Ronay

A2 - Tian, Yuanyuan

A2 - Barga, Roger

A2 - Zaniolo, Carlo

A2 - Lee, Kisung

A2 - Ye, Yanfang Fanny

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Conference on Big Data, Big Data 2019

Y2 - 9 December 2019 through 12 December 2019

ER -

Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this