Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 1, 1991Circulation

Prevention of bacterial endocarditis : a statement for health professionals from the committee on rheumatic fever, endocarditis, and Kawasaki disease of the council on cardiovascular disease in the young, the American heart association

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Does using machine learning-predicted individual educational attainment improve the prediction of cardiovascular disease hospitalization compared to ZIP code-derived education?

Population

20,805 adults from the Mount Sinai BioMe Biobank in New York City with completed questionnaires on…

Comparison

Machine learning model-predicted educational… vs ZIP code-derived educational attainment…

Design

Cohort

Follow-up

5 years

Authors

ADAdnan S. DajaniUniversity of North Carolina at Chapel HillABAlan L. BisnoUniversity of Maryland, BaltimoreKCKyung J. ChungWestern University

Discussion

Loading...

Member takes

Implication

ML-predicted education may refine SDOH-adjusted outcome models; hypothesis-generating pending prospective validation.

Structured PICO

Does using machine learning-predicted individual educational attainment improve the prediction of cardiovascular disease hospitalization compared to ZIP code-derived education?

P
Population
20,805 adults (≥25 years) from the Mount Sinai BioMe Biobank in New York City with completed questionnaires on educational attainment and home addresses, mean age 53, 58% female. A subset of 13,715 patients with a history of hospital visits was included in the cardiovascular disease hospitalization prediction models.
I
Intervention
Machine learning (ML) model-predicted educational attainment or individual survey-derived educational attainment incorporated into predictive models
C
Comparator
ZIP code-derived educational attainment incorporated into predictive models
O
Outcome
Cardiovascular disease (CVD) hospitalization within 5 years after enrollmenthard clinical

Incorporating machine learning-predicted individual educational attainment improves the accuracy of cardiovascular disease hospitalization prediction models compared to relying on ZIP code-derived education.

Cite This Study

Dajani et al. (1991) studied this question.

synapsesocial.com/papers/6a1d133528423f2ce504c1b2https://doi.org/10.1371/journal.pone.0297919
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Role of Social Determinants of Health in Risk Prediction Models for ST‐Segment–Elevation Myocardial Infarction Death: A Registry‐Based Study2026
  2. 2Enhancing cardiovascular risk prediction with neighbourhood determinants of health: a machine learning analysis in a nationwide population-based cohort of 1.8 million patients2026
  3. 3Occupational and socioeconomic predictors of myocardial infarction and coronary heart disease: a machine learning analysis2026
  4. 4Tailoring Risk Prediction Models to Local Populations2024 · 29 citations
  5. 5Examining Predictors of Myocardial Infarction2021 · 5 citations