SCORE2 cardiovascular risk prediction models in an ethnic and socioeconomic diverse population in the Netherlands: an external validation study

Kist, Janet M.; Vos, Rimke C.; Mairuhu, Albert T.A.; Struijs, Jeroen N.; Peet, Petra G. van; Vos, Hedwig M M; Os, Hendrikus J.A. van; Beishuizen, Edith D.; Sijpkens, Yvo W.J.; Faiq, Mohammad  A.; Numans, Mattijs E.; Groenwold, Rolf H H

doi:10.1016/j.eclinm.2023.101862

Cited by 17 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 2 Recent external validation in a multi-ethnic cohort in the Netherlands found underestimation of risk for both sexes, with a C -statistic of 0.70 (0.69–0.71) for men and 0.72 (0.71–0.73) for women. 15 Our O/E ratios for men and AUC results fit within this range. The SCORE2-OP model was validated in six cohorts (338 615 individuals, 33 219 events) after development and showed C -statistic for discrimination ranging between 0.63 (95% CI 0.61–0.65) and 0.67 (95% CI 0.64–0.69), comparable with our results.…”

Section: Discussionsupporting

confidence: 70%

“…The SCORE2-OP model was validated in six cohorts (338 615 individuals, 33 219 events) after development and showed C -statistic for discrimination ranging between 0.63 (95% CI 0.61–0.65) and 0.67 (95% CI 0.64–0.69), comparable with our results. 3 However, to our knowledge, none of the current validation studies for SCORE2 2 , 15–17 or SCORE2-OP 3 , 18 performed DCA to assess clinical utility.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Validation of Systematic Coronary Risk Evaluation 2 (SCORE2) and SCORE2-Older Persons in the EPIC-Norfolk prospective population cohort

van Trier,

Snaterse,

Boekholdt

et al. 2023

European Journal of Preventive Cardiology

View full text Add to dashboard Cite

Background The European Systematic Coronary Risk Evaluation 2 (SCORE2) and SCORE2-Older Persons (OP) models are recommended to identify individuals at high 10-year risk for cardiovascular disease (CVD). Independent validation and assessment of clinical utility is needed. Aim To assess discrimination, calibration and clinical utility of low-risk SCORE2 and SCORE2-OP. Methods Validation in individuals aged 40-69 years (SCORE2) and 70-79 years (SCORE2-OP) without baseline CVD or diabetes from the European Prospective Investigation of Cancer (EPIC)-Norfolk prospective population study. We compared 10-year CVD risk estimates with observed outcomes (cardiovascular mortality, non-fatal myocardial infarction and stroke). Results For SCORE2, 19,560 individuals (57% women) had 10-year CVD risk estimates of 3.7% (95% confidence interval (CI) 3.6-3.7) versus observed 3.8% (95% CI 3.6-4.1) (observed (O)/expected (E) ratio 1.0 (95% CI 1.0-1.1). The area under the curve (AUC) was 0.75 (95% CI 0.74-0.77), with underestimation of risk in men (O/E 1.4 (95% CI 1.3-1.6)) and overestimation in women (O/E 0.7 (95% CI 0.6-0.8). Decision curve analysis (DCA) showed clinical benefit. SCORE2-OP in 3,113 individuals (58% women) predicted 10-year CVD events in 10.2% (95% CI 10.1-10.3) versus observed 15.3% (95% CI 14.0-16.5) (O/E ratio 1.6 (95% CI 1.5-1.7)). The AUC was 0.63 (95% CI 0.60-0.65) with underestimation of risk across sex and risk ranges. DCA showed limited clinical benefit. Conclusion In a UK population cohort, the SCORE2 low-risk model showed fair discrimination and calibration, with clinical benefit for preventive treatment initiation decisions. In contrast, in individuals aged 70-79 years, SCORE2-OP demonstrated poor discrimination, underestimated risk in both sexes, and limited clinical utility.

show abstract

Section: Discussionsupporting

confidence: 70%

Section: Discussionmentioning

confidence: 99%

Validation of Systematic Coronary Risk Evaluation 2 (SCORE2) and SCORE2-Older Persons in the EPIC-Norfolk prospective population cohort

van Trier,

Snaterse,

Boekholdt

et al. 2023

European Journal of Preventive Cardiology

View full text Add to dashboard Cite

show abstract

“…Although the results of our model calibration were not satisfactory in external validation, two recent studies using the SCORE2 model in other European cohorts (the EPIC-Norfolk study and a cohort based on a Netherland's population) have also shown poor model calibration, suggesting that recalibration of model risk is warranted in external cohorts. 47,48 Our study also has limitations. The ESTHER study may not be the most ideal external validation cohort for our model due to differences with the UKB, particularly in the following aspects: the determination of non-fatal strokes cannot exclude hemorrhagic strokes; and regional differences in cardiovascular risk (low in UK and intermediate in Germany).…”

Section: Strengths and Limitationsmentioning

confidence: 91%

Metabolomics data improve 10-year cardiovascular risk prediction with the SCORE2 algorithm for the general population without cardiovascular disease or diabetes

Xie,

Sha,

Peng

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND: The value of metabolomic biomarkers for cardiovascular risk prediction is unclear. This study aimed to evaluate the potential of improved prediction of the 10-year risk of major adverse cardiovascular events (MACE) in large population-based cohorts by adding metabolomic biomarkers to the novel SCORE2 model, which was introduced in 2021 for the European population without previous cardiovascular disease or diabetes. METHODS: Data from 187,039 and 5,578 participants from the UK Biobank (UKB) and the German ESTHER cohort, respectively, were used for model derivation, internal and external validation. A total of 249 metabolites were measured with nuclear magnetic resonance (NMR) spectroscopy. LASSO regression with bootstrapping was used to identify metabolites in sex-specific analyses and the predictive performance of metabolites added to the SCORE2 model was primarily evaluated with Harrell's C-index. RESULTS: Thirteen metabolomic biomarkers were selected by LASSO regression for enhanced MACE risk prediction (three for both sexes, six male- and four female-specific metabolites) in the UKB derivation set. In internal validation with the UKB, adding the selected metabolites to the SCORE2 model increased the C-index statistically significantly (P<0.001) from 0.691 to 0.710. In external validation with ESTHER, the C-index increase was similar (from 0.673 to 0.688, P=0.042). The inflammation biomarker, glycoprotein acetyls, contributed the most to the increased C-index in both men and women. CONCLUSIONS: The integration of metabolomic biomarkers into the SCORE2 model markedly improves the prediction of 10-year cardiovascular risk. With recent advancements in reducing costs and standardizing processes, NMR metabolomics holds considerable promise for implementation in clinical practice.

show abstract

“…3 Although current risk prediction models using a number of traditional CVD risk factors have played an important role in CVD prevention, the predictive performance has yet to produce satisfactory results. For example, several external validation studies have demonstrated that the C -statistics of these models range only between 0.65 and 0.74, 4 , 5 and may incorrectly estimate the absolute cardiovascular risk. 4 , 6 It is known that traditional CVD risk prediction can be enhanced through additional information gained from either new predictors or repeated measurements.…”

Section: Introductionmentioning

confidence: 99%

“…For example, several external validation studies have demonstrated that the C -statistics of these models range only between 0.65 and 0.74, 4 , 5 and may incorrectly estimate the absolute cardiovascular risk. 4 , 6 It is known that traditional CVD risk prediction can be enhanced through additional information gained from either new predictors or repeated measurements. In addition to traditional predictors such as age, smoking, and systolic blood pressure (SBP), new predictors from various aetiological pathways [e.g.…”

Section: Introductionmentioning

confidence: 99%

Improving cardiovascular risk prediction through machine learning modelling of irregularly repeated electronic health records

Li,

Liu,

Shen

et al. 2023

European Heart Journal - Digital Health

View full text Add to dashboard Cite

Aims Existing electronic health records often have abundant but irregular longitudinal measurement risk factors available. We aim to leverage such data to improve the risk prediction of atherosclerotic cardiovascular disease (ASCVD) by applying machine learning algorithms, which can therefore allow the automatic screening of the population. Methods and results Totally 215,744 Chinese adults aged 40-79 without a history of CVD from an EHR-based longitudinal cohort study were included (6,081 cases). To allow the model interpretable, predictors of demographic characteristics, medication treatment, and repeatedly measured records of lipids, glycemia, obesity, blood pressure, and renal function were used. The primary outcome was ASCVD, defined as non-fatal acute myocardial infarction, coronary heart disease death, or fatal and non-fatal stroke. The eXtreme Gradient boosting (XGBoost) machine and LASSO regression models were derived to predict the 5-year ASCVD risk. In the validation set, compared with the refitted Chinese guideline-recommended Cox model (i.e., the China-PAR), the XGBoost model had significantly highest C-statistics (0.792, the difference in C-statistics: 0.011, 0.006-0.017, P<0.001), with the similar results for LASSO regression (the difference in C-statistics: 0.008, 0.005-0.011, P<0.001). The XGBoost model demonstrated the best calibration performance (Men: Dx=0.598, P=0.75; Women: Dx=1.867, P=0.08). Moreover, the machine learning algorithms’ risk distribution differed from the conventional model. The NRIs of XGBoost and LASSO over the Cox model were 3.9% (1.4%-6.4%) and 2.8% (0.7%-4.9%), respectively. Conclusions Machine learning algorithms with irregular, repeated real-world data could improve cardiovascular risk prediction. They demonstrated significantly better performance for reclassification to identify the high-risk population correctly.

show abstract

SCORE2 cardiovascular risk prediction models in an ethnic and socioeconomic diverse population in the Netherlands: an external validation study

Cited by 17 publications

References 33 publications

Validation of Systematic Coronary Risk Evaluation 2 (SCORE2) and SCORE2-Older Persons in the EPIC-Norfolk prospective population cohort

Validation of Systematic Coronary Risk Evaluation 2 (SCORE2) and SCORE2-Older Persons in the EPIC-Norfolk prospective population cohort

Metabolomics data improve 10-year cardiovascular risk prediction with the SCORE2 algorithm for the general population without cardiovascular disease or diabetes

Improving cardiovascular risk prediction through machine learning modelling of irregularly repeated electronic health records

Contact Info

Product

Resources

About