Pharmacovigilance via baseline regularization with large-scale longitudinal observational data

Zhaobin Kuang; Peggy Peissig; Vítor Santos Costa; Richard Maclin; David Page

doi:10.1145/3097983.3097998

Pharmacovigilance via baseline regularization with large-scale longitudinal observational data

Zhaobin Kuang, Peggy Peissig, Vítor Santos Costa, Richard Maclin, David Page

Computer Science (Duluth)

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

5 Scopus citations

Abstract

Several prominent public health incidents [29] that occurred at the beginning of this century due to adverse drug events (ADEs) have raised international awareness of governments and industries about pharmacovigilance (PhV) [6, 7], the science and activities to monitor and prevent adverse events caused by pharmaceutical products after they are introduced to the market. A major data source for PhV is large-scale longitudinal observational databases (LODs) [6] such as electronic health records (EHRs) and medical insurance claim databases. Inspired by the Multiple Self-Controlled Case Series (MSCCS) model [27], arguably the leading method for ADE discovery from LODs, we propose baseline regularization, a regularized generalized linear model that leverages the diverse health profiles available in LODs across different individuals at different times. We apply the proposed method as well as MSCCS to the Marshfield Clinic EHR. Experimental results suggest that incorporatingthe heterogeneity among different patients and different times help to improve the performance in identifying benchmark ADEs from the Observational Medical Outcomes Partnership ground truth [26].

Original language	English (US)
Title of host publication	KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery
Pages	1537-1546
Number of pages	10
ISBN (Electronic)	9781450348874
DOIs	https://doi.org/10.1145/3097983.3097998
State	Published - Aug 13 2017
Event	23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017 - Halifax, Canada Duration: Aug 13 2017 → Aug 17 2017

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Volume	Part F129685

Other

Other	23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017
Country/Territory	Canada
City	Halifax
Period	8/13/17 → 8/17/17

Bibliographical note

Funding Information:
Œe authors would like to gratefully acknowledge the NIH BD2K Initiative grant U54 AI117924, the NIGMS grant 2RO1 GM097618, and the P2020—Norte2020 grant NanoSTIMA/NORTE-01-0145-FEDER-00001. Œe authors would like to thank Dr. David Madigan from Columbia University for his constructive comment and advice. Œe authors would like to thank the anonymous reviewers for their reviews and feedback. Zhanrong Du and Sinong Geng from the University of Wisconsin-Madison and Dr. Shijia Wang from Harvard Medical School participated in helpful discussion. Œey are also gratefully acknowledged.

Publisher Copyright:
© 2017 Copyright held by the owner/author(s).

Keywords

Adverse drug event discovery
Baseline regularization
Electronic health records
Longitudinal data
Pharmacovigilance

Access

10.1145/3097983.3097998

OpenUrl availability

Full text

Cite this

Kuang, Z., Peissig, P., Costa, V. S., Maclin, R., & Page, D. (2017). Pharmacovigilance via baseline regularization with large-scale longitudinal observational data. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1537-1546). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Vol. Part F129685). Association for Computing Machinery. https://doi.org/10.1145/3097983.3097998

Pharmacovigilance via baseline regularization with large-scale longitudinal observational data. / Kuang, Zhaobin; Peissig, Peggy; Costa, Vítor Santos et al.
KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2017. p. 1537-1546 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Vol. Part F129685).

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

Kuang, Z, Peissig, P, Costa, VS, Maclin, R & Page, D 2017, Pharmacovigilance via baseline regularization with large-scale longitudinal observational data. in KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. Part F129685, Association for Computing Machinery, pp. 1537-1546, 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017, Halifax, Canada, 8/13/17. https://doi.org/10.1145/3097983.3097998

Kuang Z, Peissig P, Costa VS, Maclin R, Page D. Pharmacovigilance via baseline regularization with large-scale longitudinal observational data. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 2017. p. 1537-1546. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3097983.3097998

Kuang, Zhaobin ; Peissig, Peggy ; Costa, Vítor Santos et al. / Pharmacovigilance via baseline regularization with large-scale longitudinal observational data. KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2017. pp. 1537-1546 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{b8843eb61501486f934edabb213124b0,

title = "Pharmacovigilance via baseline regularization with large-scale longitudinal observational data",

abstract = "Several prominent public health incidents [29] that occurred at the beginning of this century due to adverse drug events (ADEs) have raised international awareness of governments and industries about pharmacovigilance (PhV) [6, 7], the science and activities to monitor and prevent adverse events caused by pharmaceutical products after they are introduced to the market. A major data source for PhV is large-scale longitudinal observational databases (LODs) [6] such as electronic health records (EHRs) and medical insurance claim databases. Inspired by the Multiple Self-Controlled Case Series (MSCCS) model [27], arguably the leading method for ADE discovery from LODs, we propose baseline regularization, a regularized generalized linear model that leverages the diverse health profiles available in LODs across different individuals at different times. We apply the proposed method as well as MSCCS to the Marshfield Clinic EHR. Experimental results suggest that incorporatingthe heterogeneity among different patients and different times help to improve the performance in identifying benchmark ADEs from the Observational Medical Outcomes Partnership ground truth [26].",

keywords = "Adverse drug event discovery, Baseline regularization, Electronic health records, Longitudinal data, Pharmacovigilance",

author = "Zhaobin Kuang and Peggy Peissig and Costa, {V{\'i}tor Santos} and Richard Maclin and David Page",

note = "Funding Information: {\OE}e authors would like to gratefully acknowledge the NIH BD2K Initiative grant U54 AI117924, the NIGMS grant 2RO1 GM097618, and the P2020—Norte2020 grant NanoSTIMA/NORTE-01-0145-FEDER-00001. {\OE}e authors would like to thank Dr. David Madigan from Columbia University for his constructive comment and advice. {\OE}e authors would like to thank the anonymous reviewers for their reviews and feedback. Zhanrong Du and Sinong Geng from the University of Wisconsin-Madison and Dr. Shijia Wang from Harvard Medical School participated in helpful discussion. {\OE}ey are also gratefully acknowledged. Publisher Copyright: {\textcopyright} 2017 Copyright held by the owner/author(s).; 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017 ; Conference date: 13-08-2017 Through 17-08-2017",

year = "2017",

month = aug,

day = "13",

doi = "10.1145/3097983.3097998",

language = "English (US)",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery",

pages = "1537--1546",

booktitle = "KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

}

TY - GEN

T1 - Pharmacovigilance via baseline regularization with large-scale longitudinal observational data

AU - Kuang, Zhaobin

AU - Peissig, Peggy

AU - Costa, Vítor Santos

AU - Maclin, Richard

AU - Page, David

N1 - Funding Information: Œe authors would like to gratefully acknowledge the NIH BD2K Initiative grant U54 AI117924, the NIGMS grant 2RO1 GM097618, and the P2020—Norte2020 grant NanoSTIMA/NORTE-01-0145-FEDER-00001. Œe authors would like to thank Dr. David Madigan from Columbia University for his constructive comment and advice. Œe authors would like to thank the anonymous reviewers for their reviews and feedback. Zhanrong Du and Sinong Geng from the University of Wisconsin-Madison and Dr. Shijia Wang from Harvard Medical School participated in helpful discussion. Œey are also gratefully acknowledged. Publisher Copyright: © 2017 Copyright held by the owner/author(s).

PY - 2017/8/13

Y1 - 2017/8/13

N2 - Several prominent public health incidents [29] that occurred at the beginning of this century due to adverse drug events (ADEs) have raised international awareness of governments and industries about pharmacovigilance (PhV) [6, 7], the science and activities to monitor and prevent adverse events caused by pharmaceutical products after they are introduced to the market. A major data source for PhV is large-scale longitudinal observational databases (LODs) [6] such as electronic health records (EHRs) and medical insurance claim databases. Inspired by the Multiple Self-Controlled Case Series (MSCCS) model [27], arguably the leading method for ADE discovery from LODs, we propose baseline regularization, a regularized generalized linear model that leverages the diverse health profiles available in LODs across different individuals at different times. We apply the proposed method as well as MSCCS to the Marshfield Clinic EHR. Experimental results suggest that incorporatingthe heterogeneity among different patients and different times help to improve the performance in identifying benchmark ADEs from the Observational Medical Outcomes Partnership ground truth [26].

AB - Several prominent public health incidents [29] that occurred at the beginning of this century due to adverse drug events (ADEs) have raised international awareness of governments and industries about pharmacovigilance (PhV) [6, 7], the science and activities to monitor and prevent adverse events caused by pharmaceutical products after they are introduced to the market. A major data source for PhV is large-scale longitudinal observational databases (LODs) [6] such as electronic health records (EHRs) and medical insurance claim databases. Inspired by the Multiple Self-Controlled Case Series (MSCCS) model [27], arguably the leading method for ADE discovery from LODs, we propose baseline regularization, a regularized generalized linear model that leverages the diverse health profiles available in LODs across different individuals at different times. We apply the proposed method as well as MSCCS to the Marshfield Clinic EHR. Experimental results suggest that incorporatingthe heterogeneity among different patients and different times help to improve the performance in identifying benchmark ADEs from the Observational Medical Outcomes Partnership ground truth [26].

KW - Adverse drug event discovery

KW - Baseline regularization

KW - Electronic health records

KW - Longitudinal data

KW - Pharmacovigilance

UR - http://www.scopus.com/inward/record.url?scp=85029032340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029032340&partnerID=8YFLogxK

U2 - 10.1145/3097983.3097998

DO - 10.1145/3097983.3097998

M3 - Conference contribution

C2 - 29755826

AN - SCOPUS:85029032340

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 1537

EP - 1546

BT - KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

T2 - 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017

Y2 - 13 August 2017 through 17 August 2017

ER -

Pharmacovigilance via baseline regularization with large-scale longitudinal observational data

Abstract

Publication series

Other

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this