Dataset Information

Using Integrated City Data and Machine Learning to Identify and Intervene Early on Housing-Related Public Health Problems.

ABSTRACT:

Context

Housing is more than a physical structure-it has a profound impact on health. Enforcing housing codes is a primary strategy for breaking the link between poor housing and poor health.

Objective

The objective of this study was to determine whether machine learning algorithms can identify properties with housing code violations at a higher rate than inspector-informed prioritization. We also show how city data can be used to describe the prevalence and location of housing-related health risks, which can inform public health policy and programs.

Setting

This study took place in Chelsea, Massachusetts, a demographically diverse, densely populated, low-income city near Boston.

Design

Using data from 1611 proactively inspected properties, representative of the city's housing stock, we developed machine learning models to predict the probability that a given property would have (1) any housing code violation, (2) a set of high-risk health violations, and (3) a specific violation with a high risk to health and safety (overcrowding). We generated predicted probabilities of each outcome for all residential properties in the city (N = 5989).

Results

Housing code violations were present in 54% of inspected properties, 85% of which were classified as high-risk health violations. We predict that if the city were to use integrated city data and machine learning to identify at-risk properties, it could achieve a 1.8-fold increase in the number of inspections that identify code violations as compared with current practices.

Conclusion

Given the strong connection between housing and health, reducing public health risk at more properties-without the need for additional inspection resources-represents an opportunity for significant public health gains. Integrated city data and machine learning can be used to describe the prevalence and location of housing-related health problems and make housing code enforcement more efficient, effective, and equitable in responding to public health threats.

SUBMITTER: Robb K

PROVIDER: S-EPMC8781224 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceSecondhand smoke (SHS) exposure is associated with many health conditions in children and adults. Millions of individuals in the US are currently exposed to SHS in their homes.ObjectiveTo investigate whether a federal ban on smoking in public housing settings was associated with a decrease in indoor SHS levels in New York City public housing developments 12 months after the policy's implementation.Design, setting, and participantsThis cohort study tracked indoor air quality longitudinally from April 2018 to September 2019 and used difference-in-differences analysis to examine SHS exposure before vs after implementation of the 2018 federal smoke-free housing (SFH) policy in 10 New York City Housing Authority (NYCHA) buildings vs 11 matched low-income buildings not subject to the SFH policy (ie, Section 8 buildings).ExposuresFederal SFH policy implementation, beginning July 30, 2018.Main outcomes and measuresComparison of nicotine concentration levels from passive, bisulfate-coated filters before vs 12 months after implementation of the federal SFH policy. Secondary outcomes included changes in particulate matter less than 2.5 μm in diameter, measured with low-cost particle monitors, and counts of cigarette butts in common areas.ResultsAir quality was measured repeatedly in a total of 153 NYCHA and 110 Section 8 nonsmoking households as well as in 91 stairwells and hallways. Before the SFH policy implementation, air nicotine was detectable in 19 of 20 stairwells (95.0%) in NYCHA buildings and 15 of 19 stairwells (78.9%) in Section 8 buildings (P = .19) and in 17 of 19 hallways (89.5%) in NYCHA buildings and 14 of 23 hallways (60.9%) in Section 8 buildings (P = .004). Nicotine was detected less frequently inside nonsmoking apartments overall (26 of 263 [9.9%]) but more frequently in NYCHA apartments (20 of 153 [13.1%]) than in Section 8 apartments (6 of 110 [5.5%]) (P = .04). One year after policy implementation, there was no differential change over time in nicotine concentrations measured in stairwells (DID, 0.03 μg/m3; 95% CI, -0.99 to 1.06 μg/m3) or inside nonsmoking households (DID, -0.04 μg/m3; 95% CI, -0.24 to 0.15 μg/m3). Larger decreases in nicotine concentration were found in NYCHA hallways than in Section 8 hallways (DID, -0.43 μg/m3; 95% CI, -1.26 to 0.40 μg/m3).Conclusions and relevanceThe findings suggest that there was no differential change in SHS in NYCHA buildings 12 months after SFH policy implementation. Additional support may be needed to ensure adherence to SFH policies.