The built environment and adverse cardiovascular events in US veterans with cardiovascular disease

Abstract

QUESTION: Can AI-extracted interpretable built environment features predict major adverse cardiovascular events (MACE) in a national veteran population? FINDINGS: In this cohort study of 770,990 U.S. veterans, seven built environment features were significantly associated with an increased risk of MACE. Two features, old/dilapidated buildings and visible wire, were associated with a decreased risk. Greenery was only linked to increased risk in higher social deprivation index quartiles. MEANING: Built environment features can serve as predictors of MACE, highlighting the potential role of neighborhood characteristics in cardiovascular risk stratification beyond traditional factors. IMPORTANCE: The relationship between built environment features and major adverse cardiovascular events (MACE) in patients with atherosclerotic cardiovascular disease (ASCVD) remains understudied. Our study aims to discover what specific built environmental features influence cardiovascular mortality. DESIGN: Retrospective cohort study of US Veterans (2016-2021) (98 % male, 86 % white) with stable ASCVD (coronary artery disease, cerebrovascular disease, or peripheral artery disease). EXPOSURES: Built environment features were assessed using 164 million Google Street View images (2019) sampled every 50 m across the US. Eleven features, including greenery, sidewalks, and non-single-family homes, were analyzed as the percentage of images containing each element. These were summarized at the census tract level and linked to participant healthcare data via residential addresses. OUTCOME: The primary outcome was first MACE occurrence (non-fatal myocardial infarction, non-fatal stroke, or cardiovascular mortality). Associations were analyzed using multivariable Fine Gray models, adjusting for demographics, clinical factors, the social deprivation index, and competing risks. RESULTS: Over a 4-year median follow-up, features associated with increased MACE risk included greenery (subHR: 1.054, 95 % CI: 1.047-1.061), single-lane roads (subHR: 1.059, 95 % CI: 1.054-1.065), sidewalks (subHR: 1.023, 95 % CI: 1.020-1.026), crosswalks (subHR: 1.062, 95 % CI: 1.040-1.083), non-single-family homes (subHR: 1.088, 95 % CI: 1.083-1.094), and two or more cars (subHR: 1.013, 95 % CI: 1.006-1.019). Features linked to lower MACE risk included old buildings (subHR: 0.976, 95 % CI: 0.971-0.982) and visible wiring (subHR: 0.972, 95 % CI: 0.967-0.976). CONCLUSIONS: Built environment features influence MACE risk in US Veterans with ASCVD, emphasizing the role of the exposome in cardiovascular health.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 4 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.