What does this research mean for the field?

Incorporating social determinants of health into high-performing clinical risk models does not meaningfully improve the prediction of in-hospital mortality for patients with ST-segment-elevation myocardial infarction. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To evaluate whether incorporating neighborhood-level social determinants of health into clinical risk models improves the prediction of in-hospital mortality following ST-segment-elevation myocardial infarction.

August 22, 2026Journal of the American Heart AssociationOpen Access

Role of Social Determinants of Health in Risk Prediction Models for ST‐Segment–Elevation Myocardial Infarction Death: A Registry‐Based Study

View Full Paper

Ask AI

Bookmark

Why the study?

The incremental value of social determinants of health in risk prediction models for STEMI death remained uncertain.

Does incorporating zip code-level social determinants of health improve risk prediction models for in-hospital death in STEMI patients?

Population

749 410 STEMI admissions from the GWTG-CAD registry

Comparison

Clinical model vs clinical model plus zip code-level SDOH variables

Design

Registry-based retrospective cohort study

Authors

EPElina Eleftheria PliakosCross-Cutting Cardiology KSKaitlyn ShultzUniversity of Michigan KRKriyana P. ReddyCalifornia University of Pennsylvania

Discussion

Member takes

Implication

SDOH should not yet enter STEMI mortality models; leaves open their incremental prognostic value.

Key Points

To evaluate whether incorporating neighborhood-level social determinants of health into clinical risk models improves the prediction of in-hospital mortality following ST-segment-elevation myocardial infarction.
Analyzed 749,410 STEMI admissions from the American Heart Association GWTG-CAD registry between 2018 and 2020.
Constructed multivariable logistic regression models using clinical variables alone versus clinical variables plus zip code-level SDOH metrics (education, income, poverty, foreign-born status), handling missing data with multiple imputation by chained equations.
Assessed model discrimination and incremental value using concordance statistics, area under the receiver operating characteristic curve, and DeLong's test.
Both the clinical and SDOH models showed identical discrimination for in-hospital mortality (concordance statistic = 0.95; AUROC = 0.85), indicating no meaningful overall improvement from adding SDOH variables.
Exploratory analyses showed modest statistical improvements in discrimination when individually adding high school graduation, college graduation, per-capita income, poverty, or foreign-born status, whereas median household income yielded no improvement.

Structured PICO

Does incorporating zip code-level social determinants of health improve risk prediction models for in-hospital death in STEMI patients?

Population

749,410 hospital admissions for ST-segment-elevation myocardial infarction (STEMI) between 2018 and 2020 from the American Heart Association's GWTG-CAD registry, median age 62 years, 72% men.

Intervention

Full SDOH model incorporating zip code-level social determinants of health (college graduation, high school graduation, per-capita income, poverty, foreign-born status, and median household income) in addition to clinical variables.

Comparator

Clinical model including demographic, clinical, and medical history variables.

Outcome

In-hospital STEMI death (assessed via model discrimination using concordance statistic/area under the receiver operating characteristic curve).hard clinical

Incorporating zip code-level social determinants of health into an already high-performing clinical risk model does not meaningfully improve the prediction of in-hospital mortality for STEMI patients.

Cite This Study

Pliakos et al. (2026) studied this question.

synapsesocial.com/papers/6a895fc4ca7ade938187eaa1 https://doi.org/10.1161/jaha.125.047813

View Full Paper

Ask AI

Bookmark

Role of Social Determinants of Health in Risk Prediction Models for ST‐Segment–Elevation Myocardial Infarction Death: A Registry‐Based Study

Discussion

Member takes

Implication

Key Points

Structured PICO

Cite This Study

Role of Social Determinants of Health in Risk Prediction Models for ST‐Segment–Elevation Myocardial Infarction Death: A Registry‐Based Study

Discussion

Member takes

Implication

Key Points

Structured PICO

Cite This Study

Also Consider

Also Consider