Investigating Sociodemographic Disparities in Cancer Risk Using Web-Based Informatics

Yoon, Hong-Jun; Tourassi, Georgia

doi:10.7771/2327-2937.1087

Title: Investigating Sociodemographic Disparities in Cancer Risk Using Web-Based Informatics

Full Record
Other Related Research

Abstract

Cancer health disparities due to demographic and socioeconomic factors are an area of great interest in the epidemiological community. Adjusting for such factors is important when developing cancer risk models. However, for digital epidemiology studies relying on online sources such information is not readily available. This paper presents a novel method for extracting demographic and socioeconomic information from openly available online obituaries. The method relies on tailored language processing rules and a probabilistic scheme to map subjects’ occupation history to the occupation classification codes and related earnings provided by the U.S. Census Bureau. Using this information, a case-control study is executed fully in silico to investigate how age, gender, parity, and income level impact breast and lung cancer risk. Based on 48,368 online obituaries (4,643 for breast cancer, 6,274 for lung cancer, and 37,451 cancer-free) collected automatically and a generalized cancer risk model, our study shows strong association between age, parity, and socioeconomic status and cancer risk. Although for breast cancer the observed trends are very consistent with traditional epidemiological studies, some inconsistency is observed for lung cancer with respect to socioeconomic status.

Authors:

Yoon, Hong-Jun ^[1]; Tourassi, Georgia ^[1]

Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Biomedical Sciences, Engineering, and Computing Group. Health Data Sciences Inst.

Publication Date:: 2018-01-24

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)

Sponsoring Org.:: USDOE Office of Science (SC); National Inst. of Health (NIH) (United States)

OSTI Identifier:: 1424481

Grant/Contract Number:: AC05-00OR22725; 1R01-CA170508-04

Resource Type:: Accepted Manuscript

Journal Name:: Journal of Human Performance in Extreme Environments

Additional Journal Information:: Journal Volume: 14; Journal Issue: 1; Journal ID: ISSN 2327-2937

Publisher:: Purdue University

Country of Publication:: United States

Language:: English

Subject:: 60 APPLIED LIFE SCIENCES; digital epidemiology; natural language processing; case-control study; generalized linear model; obituary; cancer mortality; breast cancer; lung cancer

Citation Formats


                    Yoon, Hong-Jun, and Tourassi, Georgia. Investigating Sociodemographic Disparities in Cancer Risk Using Web-Based Informatics.  United States: N. p., 2018. 
Web.  doi:10.7771/2327-2937.1087.

Copy to clipboard


                    Yoon, Hong-Jun, & Tourassi, Georgia. Investigating Sociodemographic Disparities in Cancer Risk Using Web-Based Informatics.  United States.  https://doi.org/10.7771/2327-2937.1087

Copy to clipboard


                    Yoon, Hong-Jun, and Tourassi, Georgia. Wed .  
"Investigating Sociodemographic Disparities in Cancer Risk Using Web-Based Informatics".  United States.  https://doi.org/10.7771/2327-2937.1087.  https://www.osti.gov/servlets/purl/1424481.

Copy to clipboard


                    
@article{osti_1424481,

  title        = {Investigating Sociodemographic Disparities in Cancer Risk Using Web-Based Informatics},

  author       = {Yoon, Hong-Jun and Tourassi, Georgia},

  abstractNote = {Cancer health disparities due to demographic and socioeconomic factors are an area of great interest in the epidemiological community. Adjusting for such factors is important when developing cancer risk models. However, for digital epidemiology studies relying on online sources such information is not readily available. This paper presents a novel method for extracting demographic and socioeconomic information from openly available online obituaries. The method relies on tailored language processing rules and a probabilistic scheme to map subjects’ occupation history to the occupation classification codes and related earnings provided by the U.S. Census Bureau. Using this information, a case-control study is executed fully in silico to investigate how age, gender, parity, and income level impact breast and lung cancer risk. Based on 48,368 online obituaries (4,643 for breast cancer, 6,274 for lung cancer, and 37,451 cancer-free) collected automatically and a generalized cancer risk model, our study shows strong association between age, parity, and socioeconomic status and cancer risk. Although for breast cancer the observed trends are very consistent with traditional epidemiological studies, some inconsistency is observed for lung cancer with respect to socioeconomic status.},

  doi          = {10.7771/2327-2937.1087},

  journal      = {Journal of Human Performance in Extreme Environments},

  number       = 1,

  volume       = 14,

  place        = {United States},

  year         = {2018},

  month        = {1}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.7771/2327-2937.1087

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

The utility of web mining for epidemiological research: studying the association between parity and cancer risk [Web Mining for Epidemiological Research. Assessing its Utility in Exploring the Association Between Parity and Cancer Risk]

Journal Article Tourassi, Georgia ; Yoon, Hong-Jun ; Xu, Songhua ; ... - Journal of the American Medical Informatics Association

Background: The World Wide Web has emerged as a powerful data source for epidemiological studies related to infectious disease surveillance. However, its potential for cancer-related epidemiological discoveries is largely unexplored. Methods: Using advanced web crawling and tailored information extraction procedures we automatically collected and analyzed the text content of 79,394 online obituary articles published between 1998 and 2014. The collected data included 51,911 cancer (27,330 breast; 9,470 lung; 6,496 pancreatic; 6,342 ovarian; 2,273 colon) and 27,483 non-cancer cases. With the derived information, we replicated a case-control study design to investigate the association between parity and cancer risk. Age-adjusted odds ratiosmore »« less
Cited by 3
https://doi.org/10.1093/jamia/ocv141

Full Text Available
A novel web informatics approach for automated surveillance of cancer mortality trends

Journal Article Tourassi, Georgia ; Yoon, Hong-Jun ; Xu, Songhua - Journal of Biomedical Informatics

Cancer surveillance data are collected every year in the United States via the National Program of Cancer Registries (NPCR) and the Surveillance, Epidemiology and End Results (SEER) Program of the National Cancer Institute (NCI). General trends are closely monitored to measure the nation’s progress against cancer. The objective of this study was to apply a novel web informatics approach for enabling fully automated monitoring of cancer mortality trends. The approach involves automated collection and text mining of online obituaries to derive the age distribution, geospatial, and temporal trends of cancer deaths in the US. Using breast and lung cancer asmore »« less
Cited by 8
https://doi.org/10.1016/j.jbi.2016.03.027
Age Disparity in Palliative Radiation Therapy Among Patients With Advanced Cancer

Journal Article Wong, Jonathan ; Xu, Beibei ; Moores Cancer Center, University of California San Diego, La Jolla, California ; ... - International Journal of Radiation Oncology, Biology and Physics

Purpose/Objective: Palliative radiation therapy represents an important treatment option among patients with advanced cancer, although research shows decreased use among older patients. This study evaluated age-related patterns of palliative radiation use among an elderly Medicare population. Methods and Materials: We identified 63,221 patients with metastatic lung, breast, prostate, or colorectal cancer diagnosed between 2000 and 2007 from the Surveillance, Epidemiology, and End Results (SEER)-Medicare linked database. Receipt of palliative radiation therapy was extracted from Medicare claims. Multivariate Poisson regression analysis determined residual age-related disparity in the receipt of palliative radiation therapy after controlling for confounding covariates including age-related differences inmore »« less
https://doi.org/10.1016/J.IJROBP.2014.03.050
Adipose tissue levels of polybrominated diphenyl ethers and breast cancer risk in Chinese women: A case–control study

Journal Article He, Yuanfang ; Peng, Lin ; Zhang, Wancong ; ... - Environmental Research

Highlights: • Associations between adipose tissue PBDE levels and breast cancer risk were assessed. • Levels of most individual PBDE congeners were higher in breast-cancer cases than controls. • Breast-cancer risk was increased with both 2nd and 3rd tertiles of BDE-47 and BDE-209 levels with a trend. • Breast-cancer risk was also increased with the 3rd tertile of BDE-28, 99, 100, 138, 153, 154, and ∑PBDE levels. • PBDE concentrations are associated with breast-cancer risk in women in Chaoshan, China. Polybrominated diphenyl ethers (PBDEs) are suspected to be associated with breast cancer risk because of their estrogenic potencies. Epidemiological studiesmore »« less
https://doi.org/10.1016/J.ENVRES.2018.07.009
Restrictive spirometry pattern among construction trade workers

Journal Article Hines, Stella E. ; Dement, John ; Cloeren, Marianne ; ... - American Journal of Industrial Medicine

Abstract Background Spirometry‐based studies of occupational lung disease have mostly focused on obstructive or mixed obstructive/restrictive outcomes. We wanted to determine if restrictive spirometry pattern (RSP) is associated with occupation and increased mortality. Methods Study participants included 18,145 workers with demographic and smoking data and repeatable spirometry. The mortality analysis cohort included 15,445 workers with known vital status and cause of death through December 31, 2016. Stratified analyses explored RSP prevalence by demographic and clinical variables and trade. Log‐binomial regression models explored RSP risk factors while controlling for important confounders such as smoking, obesity, and comorbidities. Cox regression models exploredmore »« less
https://doi.org/10.1002/ajim.23474

Similar Records