Deep transfer learning across cancer registries for information extraction from pathology reports

Mohammed Alawad; Shang Gao; John Qiu; Noah Schaefferkoetter; Jacob D. Hinkle; Hong Jun Yoon; J. Blair Christian; Xiao Cheng Wu; Eric B. Durbin; Jong Cheol Jeong; Isaac Hands; David Rust; Georgia Tourassi

doi:10.1109/BHI.2019.8834586

Deep transfer learning across cancer registries for information extraction from pathology reports

Mohammed Alawad, Shang Gao, John Qiu, Noah Schaefferkoetter, Jacob D. Hinkle, Hong Jun Yoon, J. Blair Christian, Xiao Cheng Wu, Eric B. Durbin, Jong Cheol Jeong, Isaac Hands, David Rust, Georgia Tourassi

Internal Medicine

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

14 Scopus citations

Abstract

Automated text information extraction from cancer pathology reports is an active area of research to support national cancer surveillance. A well-known challenge is how to develop information extraction tools with robust performance across cancer registries. In this study we investigated whether transfer learning (TL) with a convolutional neural network (CNN) can facilitate cross-registry knowledge sharing. Specifically, we performed a series of experiments to determine whether a CNN trained with single-registry data is capable of transferring knowledge to another registry or whether developing a cross-registry knowledge database produces a more effective and generalizable model. Using data from two cancer registries and primary tumor site and topography as the information extraction task of interest, our study showed that TL results in 6.90% and 17.22% improvement of classification macro F-score over the baseline single-registry models. Detailed analysis illustrated that the observed improvement is evident in the low prevalence classes.

Original language	English
Title of host publication	2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings
ISBN (Electronic)	9781728108483
DOIs	https://doi.org/10.1109/BHI.2019.8834586
State	Published - May 2019
Event	2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Chicago, United States Duration: May 19 2019 → May 22 2019

Publication series

Name	2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings

Conference

Conference	2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019
Country/Territory	United States
City	Chicago
Period	5/19/19 → 5/22/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Funding

This work has been supported in part by the Joint Design of Advanced Computing Solutions for Cancer (JDACS4C) program established by the U.S. Department of Energy (DOE) and the National Cancer Institute (NCI) of the National Institutes of Health. This work was performed under the auspices of the U.S. Department of Energy by Argonne National Laboratory under Contract DE-AC02-06-CH11357, Lawrence Livermore National Laboratory under Contract DEAC52-07NA27344, Los Alamos National Laboratory under Contract DE-AC5206NA25396, and Oak Ridge National Laboratory under Contract DE-AC05-00OR22725. This work has also been supported by National Cancer Institute under Contract No. HHSN261201800013I and NCI Cancer Center Support Grant (P30CA177558).

Funders	Funder number
National Institutes of Health (NIH)
Michigan State University-U.S. Department of Energy (MSU-DOE) Plant Research Laboratory
National Childhood Cancer Registry – National Cancer Institute	P30CA177558, HHSN261201800013I
Argonne National Laboratory	DE-AC02-06-CH11357
Lawrence Livermore National Laboratory	DEAC52-07NA27344
Oak Ridge National Laboratory	DE-AC05-00OR22725
Los Alamos National Laboratory	DE-AC5206NA25396

Keywords

Convolutional neural network
Information extraction
NLP
Pathology reports
Transfer learning

ASJC Scopus subject areas

Artificial Intelligence
Signal Processing
Information Systems and Management
Biomedical Engineering
Health Informatics
Radiology Nuclear Medicine and imaging

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/BHI.2019.8834586

Cite this

Alawad, M., Gao, S., Qiu, J., Schaefferkoetter, N., Hinkle, J. D., Yoon, H. J., Christian, J. B., Wu, X. C., Durbin, E. B., Jeong, J. C., Hands, I., Rust, D., & Tourassi, G. (2019). Deep transfer learning across cancer registries for information extraction from pathology reports. In 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings Article 8834586 (2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings). https://doi.org/10.1109/BHI.2019.8834586

@inproceedings{bc4f9c473b9447048d32a05507c0b3c4,

title = "Deep transfer learning across cancer registries for information extraction from pathology reports",

abstract = "Automated text information extraction from cancer pathology reports is an active area of research to support national cancer surveillance. A well-known challenge is how to develop information extraction tools with robust performance across cancer registries. In this study we investigated whether transfer learning (TL) with a convolutional neural network (CNN) can facilitate cross-registry knowledge sharing. Specifically, we performed a series of experiments to determine whether a CNN trained with single-registry data is capable of transferring knowledge to another registry or whether developing a cross-registry knowledge database produces a more effective and generalizable model. Using data from two cancer registries and primary tumor site and topography as the information extraction task of interest, our study showed that TL results in 6.90% and 17.22% improvement of classification macro F-score over the baseline single-registry models. Detailed analysis illustrated that the observed improvement is evident in the low prevalence classes.",

keywords = "Convolutional neural network, Information extraction, NLP, Pathology reports, Transfer learning",

author = "Mohammed Alawad and Shang Gao and John Qiu and Noah Schaefferkoetter and Hinkle, {Jacob D.} and Yoon, {Hong Jun} and Christian, {J. Blair} and Wu, {Xiao Cheng} and Durbin, {Eric B.} and Jeong, {Jong Cheol} and Isaac Hands and David Rust and Georgia Tourassi",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 ; Conference date: 19-05-2019 Through 22-05-2019",

year = "2019",

month = may,

doi = "10.1109/BHI.2019.8834586",

language = "English",

series = "2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings",

booktitle = "2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings",

}

Alawad, M, Gao, S, Qiu, J, Schaefferkoetter, N, Hinkle, JD, Yoon, HJ, Christian, JB, Wu, XC, Durbin, EB , Jeong, JC, Hands, I, Rust, D & Tourassi, G 2019, Deep transfer learning across cancer registries for information extraction from pathology reports. in 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings., 8834586, 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings, 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019, Chicago, United States, 5/19/19. https://doi.org/10.1109/BHI.2019.8834586

Deep transfer learning across cancer registries for information extraction from pathology reports. / Alawad, Mohammed; Gao, Shang; Qiu, John et al.
2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings. 2019. 8834586 (2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings).

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

TY - GEN

T1 - Deep transfer learning across cancer registries for information extraction from pathology reports

AU - Alawad, Mohammed

AU - Gao, Shang

AU - Qiu, John

AU - Schaefferkoetter, Noah

AU - Hinkle, Jacob D.

AU - Yoon, Hong Jun

AU - Christian, J. Blair

AU - Wu, Xiao Cheng

AU - Durbin, Eric B.

AU - Jeong, Jong Cheol

AU - Hands, Isaac

AU - Rust, David

AU - Tourassi, Georgia

PY - 2019/5

Y1 - 2019/5

N2 - Automated text information extraction from cancer pathology reports is an active area of research to support national cancer surveillance. A well-known challenge is how to develop information extraction tools with robust performance across cancer registries. In this study we investigated whether transfer learning (TL) with a convolutional neural network (CNN) can facilitate cross-registry knowledge sharing. Specifically, we performed a series of experiments to determine whether a CNN trained with single-registry data is capable of transferring knowledge to another registry or whether developing a cross-registry knowledge database produces a more effective and generalizable model. Using data from two cancer registries and primary tumor site and topography as the information extraction task of interest, our study showed that TL results in 6.90% and 17.22% improvement of classification macro F-score over the baseline single-registry models. Detailed analysis illustrated that the observed improvement is evident in the low prevalence classes.

AB - Automated text information extraction from cancer pathology reports is an active area of research to support national cancer surveillance. A well-known challenge is how to develop information extraction tools with robust performance across cancer registries. In this study we investigated whether transfer learning (TL) with a convolutional neural network (CNN) can facilitate cross-registry knowledge sharing. Specifically, we performed a series of experiments to determine whether a CNN trained with single-registry data is capable of transferring knowledge to another registry or whether developing a cross-registry knowledge database produces a more effective and generalizable model. Using data from two cancer registries and primary tumor site and topography as the information extraction task of interest, our study showed that TL results in 6.90% and 17.22% improvement of classification macro F-score over the baseline single-registry models. Detailed analysis illustrated that the observed improvement is evident in the low prevalence classes.

KW - Convolutional neural network

KW - Information extraction

KW - NLP

KW - Pathology reports

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85073032737&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073032737&partnerID=8YFLogxK

U2 - 10.1109/BHI.2019.8834586

DO - 10.1109/BHI.2019.8834586

M3 - Conference contribution

AN - SCOPUS:85073032737

T3 - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings

BT - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings

T2 - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019

Y2 - 19 May 2019 through 22 May 2019

ER -

Alawad M, Gao S, Qiu J, Schaefferkoetter N, Hinkle JD, Yoon HJ et al. Deep transfer learning across cancer registries for information extraction from pathology reports. In 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings. 2019. 8834586. (2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings). doi: 10.1109/BHI.2019.8834586

Deep transfer learning across cancer registries for information extraction from pathology reports

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this