Deep Dive: Neighborhood Stress

This post is part of a series on Social Determinants of Health

“Neighborhood stress” or neighborhood socioeconomic context, has long been a focus of public health research. The following summarizes the unique opportunities neighborhoods provide when researching health effects:

…the “meso” level of neighborhoods is of interest for three important reasons. First, many of these broader social determinants are manifested, and directly affect individuals, through neighborhood social and physical environments. Thus the study of neighborhoods provides an opportunity to understand the processes linking these broader social and economic factors … in very concrete ways. Second, the strong residential segregation by race and class that is present in the United States (and in many other countries) suggests that these neighborhood differences could be important contributors to disparities in cardiovascular disease. Last but not least, differences across neighborhoods are not “natural’ but are the result of the impact of policies (or the absence of policies) and are hence directly amenable to intervention.

source 1

Early studies have found that simply living in federally designated poverty areas led to a 50% higher all-cause mortality rate compared to individuals in non-poor areas. Researchers since then have worked to create indices of census derived variables to provide a summary score of a neighborhood’s socioeconomic advantage or disadvantages. Diez Roux et al. used a score consisting of median household income, median value of housing units, percentage of household receiving interest or investment income, percentage of people who graduated high school, and percentage of employed persons in executive, managerial or professional positions (a census classification) source 2.

While the exact causal pathways of socioeconomic neighborhood stress and individual health are beyond the scope of this post, the models are created to allow value-based organizations to take advantage of this set of literature and support their attributed members. Algorex Health has adapted the MassHealth Social Determinants of Health Risk Adjustment Model “neighborhood stress score” which is used to calculate and adjust premium and expenses for all organizations participating in Massachusetts’ Medicaid Reform efforts. The “neighborhood stress score” is a statistically derived model determined from government surveys completed as part of the US Census and American Community Survey.

Specifically, the neighborhood stress score is made up of the following components measured at the census block group level source:

  • % of families with incomes < 100% of Federal Poverty Limit (FPL)
  • % of families with incomes < 200% of FPL
  • % of adults who are unemployed
  • % of households receiving public assistance
  • % of households with no car
  • % of households with children and a single parent % of people age 25 or older who have no high school degree

Understanding the Model

Patient or Member data being onboarded to Algorex Health system will be geocoded and assigned to a census block group. This process is critical to then calculating and identifying variables for them according to the processes below.

For each state, the census variables listed above are taken for each census block group in the state. Each variable (v1, v2… v7) is standardized using the following formula: Z = (v1- mean(v1))/SD(v1)

The scores are then added S = Z1 + Z2… Z7 then standardized again.

StressScore = (s- mean(s))/SD(s)

This mimics the scoring method used in Massachusetts developed at the University of Massachusetts by Dr. Arlene Ash..

Tuning and Localization

The resulting scores normalize census block group against other census block groups but does not account for the distribution if the model is calculated patient by patient across a population. For Algorex Health clients who seek to understand the members underlying public health variables, the stress scores are recalculated using the patient distribution and not census block group distribution.


Customers can access the underlying census variables (and many more) using the geographic_attributes schema in Algorex Health. Working with an Algorex Health client, it is possible to include additional variables or repeat the principal component analysis that UMASS used to choose variables.


1: Diez Roux AV, Mujahid MS, Hirsch JA, Moore K, Moore LV. The impact of neighborhoods on cardiovascular risk: the MESA Neighborhood Study. Global heart. 2016;11(3):353–363. doi:10.1016/j.gheart.2016.08.002. 2: Diez Roux AV et al. Neighborhood of Residence and Incidence of Coronary Heart Disease N Engl J Med 2001:345–99–106 July 12, 2001