Related Experiment Video
Updated: Aug 6, 2026
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Large-Scale Plasma Proteomics Profiles for Predicting Atrial Fibrillation Associated Stroke Risk : Type of
Shengkang Huang1, Xin Feng2, Huilin Wu3
1Department of Cardiovascular Surgery, Fuwai Hospital, National Center for Cardiovascular Diseases, National Clinical Research Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
Insights
A new five-protein score improves stroke risk prediction in atrial fibrillation (AF) patients beyond the standard CHA₂DS₂-VASc score. This protein score offers valuable insights for assessing post-AF stroke risk.
Area of Science:
- Cardiovascular Medicine
- Proteomics
- Biomarker Discovery
Background:
- Stroke is a significant complication of atrial fibrillation (AF).
- Current risk prediction scores like CHA₂DS₂-VASc have limitations in predicting stroke risk.
- Residual heterogeneity in stroke risk prediction necessitates novel approaches.
Purpose of the Study:
- To identify plasma proteins associated with stroke in AF patients.
- To evaluate if a novel protein score offers incremental predictive value over CHA₂DS₂-VASc.
- To assess the clinical utility of a protein-based risk stratification tool.
Main Methods:
- Analysis of 709 AF participants from the UK Biobank Pharma Proteomics Project.
- Identification of stroke-related proteins using Cox regression and machine learning.
- Construction and validation of a five-protein score, assessing its incremental predictive value.
Main Results:
- Five core proteins (EGFR, ATP6V1D, NTF4, AMN, DCBLD2) were identified.
- The five-protein score significantly improved stroke risk discrimination (concordance index from 0.681 to 0.768).
- The combined score demonstrated favorable calibration and reclassification improvements.
Conclusions:
- A five-protein score provides incremental predictive information for post-AF stroke risk.
- This protein score enhances risk assessment beyond the existing CHA₂DS₂-VASc score.
- The findings support the use of proteomic biomarkers in AF stroke risk stratification.
Background:
Stroke is a major complication of atrial fibrillation (AF), and risk prediction using the congestive heart failure, hypertension, age, diabetes, stroke, vascular disease, and sex category score (CHA₂DS₂-VASc) remains limited by residual heterogeneity. We aimed to identify plasma proteins associated with post-AF stroke and evaluate whether a protein score provides incremental predictive information beyond CHA₂DS₂-VASc.
Methods:
We analyzed 709 AF participants from the UK Biobank Pharma Proteomics Project, with 76 incident strokes. Stroke-related proteins were identified using multivariable Cox regression, least absolute shrinkage and selection operator (LASSO) Cox regression, and machine-learning approaches. A five-protein score was constructed, and its incremental value beyond CHA₂DS₂-VASc was assessed by discrimination, calibration, reclassification, clinical net benefit, and 1000-bootstrap internal validation. Mendelian randomization served as supportive genetic evidence.
Results:
Five core proteins were identified: epidermal growth factor receptor (EGFR), V-type proton ATPase subunit D (ATP6V1D), neurotrophin 4 (NTF4), amnionless (AMN), and discoidin, CUB and LCCL domain-containing protein 2 (DCBLD2). Adding the five-protein score to CHA₂DS₂-VASc improved discrimination, increasing the concordance index from 0.681 to 0.768. The combined model had 3-, 5-, and 8-year receiver operating characteristic areas of 0.799, 0.775, and 0.806, respectively, and showed favorable five-year prediction error and calibration, with a Brier score of 0.0347, calibration intercept of -0.068, and calibration slope of 0.968. The score improved continuous net reclassification improvement (0.459; P = 0.028). Mendelian randomization provided supportive genetic evidence for AMN, EGFR, and DCBLD2.
Conclusions:
The five-protein score provided incremental predictive information beyond CHA₂DS₂-VASc for post-AF stroke risk assessment.