Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Mar;7(1):128-137.
doi: 10.26502/fjhs.171. Epub 2024 Feb 17.

County Mammogram Uptake can be Predicted from Social Determinants of Health, but Patterns Do Not Hold for Individual Patients

Matthew Davis  1 , Kit Simpson  2 , Vanessa Diaz  3 , Alexander V Alekseyenko  1
Affiliations

County Mammogram Uptake can be Predicted from Social Determinants of Health, but Patterns Do Not Hold for Individual Patients

Matthew Davis et al. Fortune J Health Sci. 2024 Mar.

Abstract

Purpose: The objective of this study is to describe patterns in barriers to breast cancer screening uptake with the end goal of improving screening adherence and decreasing the burden of mortality due to breast cancer. This study looks at social determinants of health and their association to screening and mortality. It also investigates the extent that models trained on county data are generalizable to individuals.

Methods: County level screening uptake and age adjusted mortality due to breast cancer are combined with the Centers for Disease Controls Social Vulnerability Index (SVI) to train a model predicting screening uptake rates. Patterns learned are then applied to de-identified electronic medical records from individual patients to make predictions on mammogram screening follow through.

Results: Accurate predictions can be made about a county's breast cancer screening uptake with the SVI. However, the association between increased screening, and decreased age adjusted mortality, doesn't hold in areas with a high proportion of minority residents. It is also shown that patterns learned from county SVI data have little discriminative power at the patient level.

Conclusion: This study demonstrates that social determinants in the SVI can explain much of the variance in county breast cancer screening rates. However, these same patterns fail to discriminate which patients will have timely follow through of a mammogram screening test. This study also concludes that the core association between increased screening and decreased age adjusted mortality does not hold in high proportion minority areas.

Objective: The objective of this study is to describe patterns in social determinants of health and their association with female breast cancer screening uptake, age adjusted breast cancer mortality rate and the extent that models trained on county data are generalizable to individuals.

Keywords: Center for Disease Control (CDC); Social Vulnerability Index (SVI); directed acyclic graph (DAG); social determinants of health (SDOH).

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: The authors have no conflicts of interest to disclose.

Figures

Figure 1:
Figure 1:
Study design for translation county level mammogram screening uptake to patient level screening follow through. The top boxes show 4 county level data sets being merged and discretized, and used to train a model predicting county breast cancer screening uptake. The remained CDC SVI Census tract data set was then merged with MUSC Patient data, where the trained model was used to make predictions on which patients would actually follow through on mammogram screening.
Figure 2:
Figure 2:
Network of Factors Influencing Mammogram Screening and Age Adjusted Mortality from Breast Cancer. The proportion of patients that went unscreened in a county the class node, which all other nodes have edges, due the TAN network constraints. This shows that percentile minority is a confounding the association of age adjusted mortality and proportion of patients in a county that have received mammogram screening. Also notable is that network structure learned encoded poverty, percentile income, percentile of not having high school diplomas, unemployment, and low vehicle ownership as being associated with each other.
Figure 3:
Figure 3:
This shows the difference in mammogram screening uptake between counties with high proportion of people over age 65 vs not, for each RUC code with the 25th, 50th, and 75th percentiles marked as the box, and the whisker bars as 1.5x the interquartile range. This demonstrates consistently higher screening rates in counties with older populations at each Rural-Urban Continuum level.
Figure 4:
Figure 4:
This shows female age adjusted mortality due to breast cancer plotted with the percent of persons that went unscreened. When the proportion of females that are un screened goes up, the age adjusted mortality also increases for areas not in the highest proportion on minority shown in the left panel. This association is no true for high proportion minority areas where the association of screening and age adjusted mortality is uncertain.
Figure 5:
Figure 5:
Model Trained on County Screening Uptake Have a Poor Ability to Discriminate Between Patients that Will or Will Not Complete a Mammogram Screening After Ordered by a Provided.
See this image and copyright information in PMC

Update of

Similar articles

See all similar articles

References

    1. CDCBreastCancer. An Update on Cancer Deaths in the United States. Centers for Disease Control and Prevention. Published February 28, 2022. Accessed April 28 (2022).
    1. Roumeliotis S, Abd ElHafeez S, Jager KJ, et al. Be careful with ecological associations. Nephrol Carlton Vic 26 (2021): 501–505. - PubMed
    1. Gerend MA, Pai M. Social Determinants of Black-White Disparities in Breast Cancer Mortality: A Review. Cancer Epidemiol Biomarkers Prev 17 (2008): 2913–2923. - PubMed
    1. Heller SL, Rosenkrantz AB, Gao Y, Moy L. County-Level Factors Predicting Low Uptake of Screening Mammography. AJR Am J Roentgenol 211 (2018): 624–629. - PubMed
    1. Pearl J An Introduction to Causal Inference. Int J Biostat 6 (2010): 7. - PMC - PubMed

LinkOut - more resources