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
. 2022 Feb 21:2021:1149-1158.
eCollection 2021.

The Addition of United States Census-Tract Data Does Not Improve the Prediction of Substance Misuse

Daniel To  1 , Cara Joyce  2 , Sujay Kulshrestha  3 , Brihat Sharma  4 , Dmitry Dligach  2   5 , Matthew Churpek  6 , Majid Afshar  6
Affiliations

The Addition of United States Census-Tract Data Does Not Improve the Prediction of Substance Misuse

Daniel To et al. AMIA Annu Symp Proc. .

Abstract

Predictors from the structured data in the electronic health record (EHR) have previously been used for case-identification in substance misuse. We aim to examine the added benefit from census-tract data, a proxy for socioeconomic status, to improve identification. A cohort of 186,611 hospitalizations was derived between 2007 and 2017. Reference labels included alcohol misuse only, opioid misuse only, and both alcohol and opioid misuse. Baseline models were created using 24 EHR variables, and enhanced models were created with the addition of 48 census-tract variables from the United States American Community Survey. The absolute net reclassification index (NRI) was applied to measure the benefit in adding census-tract variables to baseline models. The baseline models already had good calibration and discrimination. Adding census-tract variables provided negligible improvement to sensitivity and specificity and NRI was less than 1% across substance groups. Our results show the census-tract added minimal value to prediction models.

PubMed Disclaimer

Figures

Figure 1a-c.
Figure 1a-c.
Classification plots for models with and without census-tract variables for (a) Alcohol-only; (b) Opioid-only, and (c) Alcohol and Opioid misuse.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Fingar KR, Barrett ML, Jiang JH. Comparison of All-Cause 7-Day and 30-Day Readmissions, 2014. The HCUP Report : Healthcare Cost and Utilization Project (HCUP): Statistical Briefs. 2017. ASI 4186-20.230;Statistical Brief No. 230. 2017.
    1. Wilson N, Kariisa M, Seth P, Smith 4, Herschel, Davis NL. Drug and Opioid-Involved Overdose Deaths - United States, 2017-2018. MMWR. Morbidity and mortality weekly report. 2020 Mar 20;69(11):290–297. - PMC - PubMed
    1. Collins SE. Associations Between Socioeconomic Factors and Alcohol Outcomes. Alcohol research. 2016;38(1):83–94. - PMC - PubMed
    1. Grittner U, Kuntsche S, Graham K, Bloomfield K. Social Inequalities and Gender Differences in the Experience of Alcohol-Related Problems. Alcohol and alcoholism (Oxford) 2012;47(5):597–605. - PMC - PubMed
    1. Compton WM, Gfroerer J, Conway KP, Finger MS. Unemployment and substance outcomes in the United States 2002–2010. Drug and Alcohol Dependence. 2014;142:350–353. - PMC - PubMed

LinkOut - more resources