PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 16, 2026JAMA Network Open4 citationsOpen Access

Performance of PREVENT Cardiovascular Risk in Electronic Health Record–Based Clinical Practice

View Full Paper
CHChuan HongMNMu NiuHWH Z Wang

Key Result

The PREVENT equations showed strong cardiovascular risk discrimination, with C-indices of 0.77 for both sexes in complete records and 0.75 to 0.77 when using imputed missing data.

Key Points

  • Evaluate the performance of PREVENT equations in predicting cardiovascular disease risk using EHR data.
  • Conducted a retrospective cohort study using data from Duke University Health System.
  • Defined relaxed and strict cohorts based on data completeness for analysis.
  • Utilized published PREVENT equations and local adaptations to assess discrimination and calibration.
  • PREVENT equations exhibited strong discrimination with C-indices of 0.77 in the strict cohort and 0.75 in the relaxed cohort.
  • Calibration ratios indicated higher accuracy in the strict cohort, suggesting risk underestimation in the relaxed cohort.
  • Local adaptations improved calibration modestly without significantly affecting discrimination.

Structured PICO

Do the PREVENT equations accurately predict 5-year incident CVD risk in a real-world electronic health record cohort with and without missing data?

P
Population
406,230 patients without baseline cardiovascular disease (CVD) with sufficient data to calculate PREVENT risk in an electronic health record cohort. Divided into a relaxed cohort (n=406,230; mean age 49, 59% female) and a strict cohort restricted to complete records (n=127,151; mean age 53-54, 56% female).
I
Intervention
PREVENT (Predicting Risk of Cardiovascular Disease Events) equations for cardiovascular disease risk prediction
C
Comparator
Locally fitted Cox proportional hazards, discrete-time neural network, and recalibrated PREVENT models
O
Outcome
Estimated 5-year risk of incident CVD, assessed via discrimination (C-index) and calibration (expected vs observed event rates) at 5 years

The PREVENT equations demonstrate strong discrimination for 5-year CVD risk in real-world EHR data, remaining robust even when missing laboratory and vital sign data are imputed.

Abstract

ImportanceIn 2023, the American Heart Association Cardiovascular-Kidney-Metabolic Scientific Advisory Group introduced the Predicting Risk of Cardiovascular Disease Events (PREVENT) equations, a race-free, sex-specific model for cardiovascular disease (CVD) risk prediction in adults aged 30 to 79 years. While initial validations showed strong performance, their reliability under missingness conditions remains unclear.ObjectiveTo evaluate discrimination and calibration of the PREVENT equations in an electronic health record (EHR) cohort and assess robustness to missingness.Design, Setting, and ParticipantsThis retrospective cohort study used Duke University Health System, a health network encompassing tertiary hospitals, regional hospitals, and primary care practices across North Carolina, EHR data from March 2014 to December 2024 with up to 8 years follow-up. Patients without baseline CVD with sufficient data to calculate PREVENT risk were included. Two cohorts were defined: a relaxed cohort, allowing for missing laboratory and vital sign data with race-sex median imputation, and a strict cohort, restricted to those with complete records. Data were analyzed from October 2024 to June 2025.ExposuresPublished PREVENT equations alongside locally fitted Cox proportional hazards, discrete-time neural network, and recalibrated PREVENT models.Main Outcomes and MeasuresThe primary outcomes were estimated 5-year risk of incident CVD and assessed discrimination (C-index) and calibration (expected vs observed event rates) at 5 years by race, sex, and socioeconomic subgroups. The local adaptation via Duke retraining was compared with machine learning–based recalibration of PREVENT scores.ResultsThe study included 406 230 patients in the relaxed cohort (239 764 females with a mean SD age of 49 20 years and 166 466 males with a mean SD age of 49 20 years; 16 291 Asian 4.0%, 107 114 Black 26.4%, and 256 403 White 63.1%) and 127 151 patients in the strict cohort (71 086 females with a mean SD age of 54 13 years and 56 065 males with a mean SD age of 53 12 years; 8210 Asian 6.5%, 29 033 Black 22.8%, and 83 515 White 65.7%). PREVENT showed strong discrimination in both cohorts (C-index, 0.77 for both males and females in the strict cohort vs 0.75 for males and 0.77 for females in the relaxed cohort), indicating robustness to missing data. Calibration ratios were higher in the strict cohort, indicating more risk underestimation in the relaxed cohort. Local adaptations minimally affected discrimination and modestly improved calibration.Conclusions and RelevanceIn this cohort study, the PREVENT equations showed strong discrimination and generalizability, including with missing laboratory and vital sign data when imputation was applied, supporting reliable CVD risk identification and ranking in routine practice.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Hong et al. (2026) studied this question. The PREVENT equations showed strong cardiovascular risk discrimination, with C-indices of 0.77 for both sexes in complete records and 0.75 to 0.77 when using imputed missing data.

synapsesocial.com/papers/69e07d732f7e8953b7cbe630https://doi.org/10.1001/jamanetworkopen.2026.6838
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

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

  1. 1Review of Predicting Risk of Cardiovascular Disease EVENTs (PREVENT)2026
  2. 2External Validation of the PREVENT Equations in a National Sample of US Adults2026
  3. 3Performance of PREVENT equations for cardiovascular risk prediction in young patients with myocardial infarction: From the MGB YOUNG-MI registry2025 · 11 citations
  4. 4Multinational validation of the PREVENT and SCORE2 cardiovascular risk equations across 6.4 million individuals2026 · 10 citations
  5. 5External validation of the 2023 American Heart Association Predicting Risk of cardiovascular disease EVENTs equations for atherosclerotic cardiovascular disease in primary cardiovascular prevention setting and comparison with 2021 Systematic COronary Risk Evaluation and 2013 Pooled Cohort Equations2025 · 2 citations