by Luke Shulman

Social Determinants and Neighborhoods

Social determinants of health (SDOH) are “the structural determinants and conditions in which people are born, grow, live, work and age.”via KFF. They are receiving increased attention as healthcare organizations begin to increasingly emphasize population health and value-based payment models. For Algorex Health customers, social determinants are moving to the forefront as several value-based payment programs, especially in Medicaid, begin to use social determinants to directly effect payment through risk-adjustment.

A recent study the by Commonwealth Fund profiled programs in eight states that were collecting new social determiants data and using it in the risk adjustment and premium calculation for their Medicaid programs. The following chart from that study shows the type of SDOH data being collected and used in these state programs:

In a concerning finding, the authors found “Such efforts are relatively nascent, and therefore standardized measures and a consistent approach to measuring SDOH have not yet been adopted.24 In the absence of a commonly accepted definition and standardized SDOH measures, there is significant variation in how states are collecting, using, and reporting this information (Exhibit 3). This variation is similar to the early movement toward standardized clinical quality measurement.”

One of the more prominent uses of SDOH data, in Medicaid, is starting right here in Massachusetts. For 2017, the state, responding to comments from previous years, is using a newly revamped risk adjustment algorithm using SDOH data prominently alongside diagnosis and demographic data. The MassHealth Social Determinants of Health Risk Adjustment Model will be used to calculate and adjust premium and expenses for all organizations participating in Massachusetts’ Medicaid reform efforts. One of the most prominent new variables in the risk adjustment model is “neighborhood stress score” which is a statistically derived score 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 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

Given that this is based on open data from the US Census Bureau, we decided to chart the neighborhood stress score for every census block in Massachusetts (darker equals higher stress score):

Massachusetts Neighborhood Stress Scores by Census Block

In a follow-up post, I will detail the technical details behind this because it gave us a chance to try new libraries for geospatial analysis in Python, specifically folium and geopandas.

If you are working on social determinants contact us at Algorex Health. Our licensed data sets can help fill in missing social and demographic data on your patients and also teach you to make beautiful maps like these in no time.