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

Systematic Coronary Risk Evaluation 2 for Older Persons: 10 years risk validation, clinical utility, and potential improvement

AIMS

European Systematic Coronary Risk Assessment 2 for Older Persons (SCORE2-OP) model has shown modest performance when externally validated in selected cohorts. We aim to investigate its predictive performance and clinical utility for 10-year cardiovascular (CV) risk in an unbiased and representative cohort of older people of a low CV risk country. Furthermore, we explore whether other clinical or echocardiographic features could improve its performance.

METHODS AND RESULTS

A cohort of randomly selected individuals ≥65 years from a primary care population of Barcelona without established CV disease included 791 patients (63.1% female, median age 76 years, median follow-up 11.8 years). The model's performance yielded a Harrell's C-statistic of 0.706 (95% confidence interval [CI] 0.659-0.753) for the primary endpoint (myocardial infarction, stroke, and CV mortality) and 0.692 (95% CI 0.649-0.734) for the secondary endpoint (primary endpoint plus heart failure hospitalization), with better discrimination in females. SCORE2-OP underestimated the risk of primary endpoint in women [expected/observed (E/O) = 0.77], slightly overestimated in men (E/O = 1.06), and systematically underestimated the risk of the secondary endpoint (E/O = 0.52). Decision curve analysis showed net clinical benefit across a 7.5-30% risk range for primary endpoint. Valvular calcification was the only variable that significantly improved 10-year SCORE2-OP risk performance for both primary and secondary endpoints, with a change in Harrell's C of 0.028 (P = 0.017).

CONCLUSION

In a low CV risk country, SCORE2-OP showed notable discrimination and excellent calibration to predict 10-year CV risk, with better performance in females. Incorporating valvular calcification in a future revised score may enhance accuracy and reduce unnecessary treatments.

External validation and comparison of six cardiovascular risk prediction models in the Prospective Urban Rural Epidemiology (PURE)-Colombia study

AIMS

To externally validate the SCORE2, AHA/ACC pooled cohort equation (PCE), Framingham Risk Score (FRS), Non-Laboratory INTERHEART Risk Score (NL-IHRS), Globorisk-LAC, and WHO prediction models and compare their discrimination and calibration capacity.

METHODS AND RESULTS

Validation in individuals aged 40-69 years with at least 10 years of follow-up and without baseline use of statins or cardiovascular diseases from the Prospective Urban Rural Epidemiology (PURE)-Colombia prospective cohort study. For discrimination, the C-statistic, and receiver operating characteristic curves with the integrated area under the curve (AUCi) were used and compared. For calibration, the smoothed time-to-event method was used, choosing a recalibration factor based on the integrated calibration index (ICI). In the NL-IHRS, linear regressions were used. In 3802 participants (59.1% women), baseline risk ranged from 4.8% (SCORE2 women) to 55.7% (NL-IHRS). After a mean follow-up of 13.2 years, 234 events were reported (4.8 cases per 1000 person-years). The C-statistic ranged between 0.637 (0.601-0.672) in NL-IHRS and 0.767 (0.657-0.877) in AHA/ACC PCE. Discrimination was similar between AUCi. In women, higher over-prediction was observed in the Globorisk-LAC (61%) and WHO (59%). In men, higher over-prediction was observed in FRS (72%) and AHA/ACC PCE (71%). Overestimations were corrected after multiplying by a factor derived from the ICI.

CONCLUSION

Six prediction models had a similar discrimination capacity, supporting their use after multiplying by a correction factor. If blood tests are unavailable, NL-IHRS is a reasonable option. Our results suggest that these models could be used in other countries of Latin America after correcting the overestimations with a multiplying factor.

External validation of SCORE2-Diabetes in The Netherlands across various socioeconomic levels in native-Dutch and non-Dutch populations

AIMS

Adults with type 2 diabetes have an increased risk of cardiovascular events (CVEs), the world's leading cause of mortality. The SCORE2-Diabetes model is a tool designed to estimate the 10-year risk of CVE specifically in individuals with type 2 diabetes. However, the performance of such models may vary across different demographic and socioeconomic groups, necessitating validation and assessment in diverse populations. This study aims to externally validate SCORE2-Diabetes and assess its performance across various socioeconomic and migration origins in The Netherlands.

METHODS AND RESULTS

We selected adults with type 2 diabetes, aged 40-79 years and without previous CVE from the Extramural LUMC Academic Network (ELAN) primary care data cohort from 2007 to 2023. ELAN data were linked with Statistics Netherlands registry data to obtain information about the country of origin and socioeconomic status (SES). Cardiovascular event was defined as myocardial infarction, stroke, or CV mortality. Non-CV mortality was considered a competing event. Analyses were stratified by sex, Dutch vs. other non-Dutch countries of origin, and quintiles of SES. Of the 26 544 included adults with type 2 diabetes, 2518 developed CVE. SCORE2-Diabetes showed strong predictive accuracy for CVE in the Dutch population [observed-to-expected ratio (OE) = 1.000, 95% CI = 0.990-1.008 for men, and OE = 1.050, 95% CI = 1.042-1.057 for women]. For non-Dutch individuals, the model underestimated CVE risk (OE = 1.121, 95% CI = 1.108-1.131 for men, and OE = 1.100, 95% CI = 1.092-1.111 for women). The model also underestimated the CVE risk (OE > 1) in low SES groups and overestimated the risk (OE < 1) in high SES groups. Discrimination was moderate across subgroups with c-indices between 0.6 and 0.7.

CONCLUSION

SCORE2-Diabetes accurately predicted the risk of CVE in the Dutch population. However, it underpredicted the risk of CVE in the low SES groups and non-Dutch origins, while overpredicting the risk in high SES men and women. Additional clinical judgment must be considered when using SCORE2-Diabetes for different SES and countries of origin.

LAY SUMMARY

A new study validates the SCORE2-Diabetes model for predicting a 10-year risk of cardiovascular events in type 2 diabetes. Strong accuracy for the Dutch population, but underestimation of the risk for low SES and non-Dutch groups. SCORE2-Diabetes should be used with extra caution across diverse subgroups.

Integration of apolipoprotein B into the SCORE2 framework: implications for cardiovascular risk prediction

AIMS

To evaluate whether integrating Apolipoprotein B (ApoB) into the Systematic Coronary Risk Evaluation 2 (SCORE2) cardiovascular risk prediction framework improves its predictive accuracy and clinical applicability within the UK Biobank population.

METHODS AND RESULTS

A 10-year prospective cohort study was conducted with 448 303 UK Biobank participants eligible for SCORE2 calculation. Three approaches were employed: (i) threshold analysis to determine the optimal ApoB cutoff for cardiovascular disease (CVD) risk prediction using Youden's Index, (ii) assessment of the synergistic effect of SCORE2 and ApoB through concordant and discordant classifications, and (iii) recalibration of the SCORE2 model by incorporating ApoB as an additional predictor. Each 0.2 g/L increase in ApoB was associated with an increased subdistribution hazard for CVD events [subdistribution hazard ratio (SHR): 1.13; 95% CI: 1.11-1.14, P < 0.001], accounting for non-cardiovascular death as a competing risk. Threshold analysis identified an optimal ApoB cutoff at 1.18 g/L; however, it demonstrated limited discriminatory performance (area under the curve 0.54), with low sensitivity (32.4%), and moderate specificity (74.4%). Individuals with both low ApoB (<1.18 g/L) and low SCORE2 risk (<5%) had a lower CVD incidence rate (232.51 per 100 000 person-years) compared with those identified as low risk by SCORE2 alone (253.69 per 100 000 person-years). Integration of ApoB into the SCORE2 model did not significantly improve the model discrimination, calibration, and net reclassification improvement.

CONCLUSION

Apolipoprotein B exhibited a dose-response relationship with cardiovascular risk but had limited standalone predictive utility within the UK Biobank population. However, combining ApoB with SCORE2 thresholds improved the identification of low-risk individuals, suggesting a complementary role for ApoB in refining cardiovascular risk stratification.

Addressing underestimation and explanation of retinal fundus photo-based cardiovascular disease risk score: Algorithm development and validation

OBJECTIVE

To resolve the underestimation problem and investigate the mechanism of the AI model which employed to predict cardiovascular disease (CVD) risk scores from retinal fundus photos.

METHODS

An ordinal regression Deep Learning (DL) model was proposed to predict 10-year CVD risk scores. The mechanism of the DL model in understanding CVD risk was explored using methods such as transfer learning and saliency maps.

RESULTS

Model development was performed using data from 34,652 participants with good-quality fundus photographs from the UK Biobank and a dataset for external validation collected in Australia comprised of 1376 fundus photos of 401 participants with a desktop retinal camera and a portable retinal camera. The mean [SD] risk-level accuracies across cross-validation folds was 0.772 [0.008], while AUROC for over moderate risk was 0.849 [0.005] and the AUROC for high risk was 0.874 [0.007] on the UK Biobank dataset. The risk-level accuracy for images acquired with the desktop camera data was 0.715, and the accuracy for portable camera data was 0.656 on the external dataset.

CONCLUSIONS

The DL model described in this study has minimized the underestimation problem. Our analysis confirms that the DL model learned CVD risk score prediction primarily from age- and sex-related image representation. Model performance was only slightly degraded when features such as the retinal vessels and colours were removed from the images. Our analysis identified some image features associated with high CVD risk status, such as the peripheral small vessels and the macula areas.

Scoping review of the use of multimorbidity variables in cardiovascular disease risk prediction

BACKGROUND

Cardiovascular disease (CVD) is a leading cause of morbidity and mortality globally. Many countries use pooled cohort equations or similar risk prediction models to assess atherosclerotic CVD risk to guide preventive measures. There is evidence that clinical CVD risk prediction equations are less accurate for adults with higher levels of multimorbidity (the co-occurrence of multiple long-term conditions). Operating within a single disease paradigm may not be appropriate for adults with multimorbidity who may be at higher risk of both CVD and non-CVD death. This scoping review was conducted to gather evidence on the inclusion of multimorbidity measures in CVD risk models to assess their methodology and identify evidence gaps in the literature.

METHODS

The review covers literature from 1 January 2012 to 23 September 2022, using the Arksey and O'Malley framework. We searched MEDLINE, Embase, and Cochrane databases published during this period and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) reporting guidelines.

RESULTS

This review identified fourteen studies reporting multivariable prognostic CVD models that included a multimorbidity variable. Of these, four studies specifically looked at the added benefit of a multimorbidity variable in a CVD risk model. Only one of these studies was conducted in a primary prevention cohort (i.e., people were free of CVD at baseline). This scoping review revealed several primary evidence gaps, notably the limited literature on the topic, the model performance in ethnic subpopulations, and the comparative assessment of alternative multimorbidity variables beyond the Charlson Comorbidity Index.

CONCLUSIONS

Few studies have assessed the impact of incorporating multimorbidity indices in primary and secondary prevention cohorts. Future research is needed to evaluate the incremental value of multimorbidity indices in cardiovascular disease risk prediction models to inform risk stratification and management strategies in people with multimorbidity.

Risk prediction of cardiovascular disease in the Asia-Pacific region: the SCORE2 Asia-Pacific model

BACKGROUND AND AIMS

To improve upon the estimation of 10-year cardiovascular disease (CVD) event risk for individuals without prior CVD or diabetes mellitus in the Asia-Pacific region by systematic recalibration of the SCORE2 risk algorithm.

METHODS

The sex-specific and competing risk-adjusted SCORE2 algorithms were systematically recalibrated to reflect CVD incidence observed in four Asia-Pacific risk regions, defined according to country-level World Health Organization age- and sex-standardized CVD mortality rates. Using the same approach as applied for the original SCORE2 models, recalibration to each risk region was completed using expected CVD incidence and risk factor distributions from each region.

RESULTS

Risk region-specific CVD incidence was estimated using CVD mortality and incidence data on 8 405 574 individuals (556 421 CVD events). For external validation, data from 9 560 266 individuals without previous CVD or diabetes were analysed in 13 prospective studies from 12 countries (350 550 incident CVD events). The pooled C-index of the SCORE2 Asia-Pacific algorithms in the external validation datasets was .710 [95% confidence interval (CI) .677-.744]. Cohort-specific C-indices ranged from .605 (95% CI .597-.613) to .840 (95% CI .771-.909). Estimated CVD risk varied several-fold across Asia-Pacific risk regions. For example, the estimated 10-year CVD risk for a 50-year-old non-smoker, with a systolic blood pressure of 140 mmHg, total cholesterol of 5.5 mmol/L, and high-density lipoprotein cholesterol of 1.3 mmol/L, ranged from 7% for men in low-risk countries to 14% for men in very-high-risk countries, and from 3% for women in low-risk countries to 13% for women in very-high-risk countries.

CONCLUSIONS

The SCORE2 Asia-Pacific algorithms have been calibrated to estimate 10-year risk of CVD for apparently healthy people in Asia and Oceania, thereby enhancing the identification of individuals at higher risk of developing CVD across the Asia-Pacific region.

Tinnitus is not associated with cardiovascular risk factors or mortality in the Gutenberg Health Study

BACKGROUND AND AIMS

Tinnitus, characterized by the conscious perception of sound without external acoustic stimulation, presents a multifaceted challenge. Recent research suggests a potential association between tinnitus and cardiovascular health. To elucidate these associations further, we examined the prevalence of tinnitus alongside its distress levels and their associations with cardiovascular risk factors, diseases, and risk of death within a general population cohort.

METHODS AND RESULTS

This study analyzed data from the prospective Gutenberg Health Study (GHS), a population-based cohort of 15,010 individuals aged 35-74, who underwent baseline assessments from 2007 to 2012. We focused on the 10-year follow-up (2017-2020) of the GHS, including otologic testing with 8539 subjects, of whom 2387 (28%) reported tinnitus, allowing for a comprehensive cross-sectional and prospective analysis. Participants completed a questionnaire on hearing-related symptoms, including tinnitus presence ("Do you suffer from ringing in the ears (tinnitus)?" yes/no) and distress ("How much do you feel bothered by it?"), rated on a six-point scale from 0 ("not bothersome") to 5 ("very bothersome"). Outcomes were assessed based on observed prevalent cardiovascular conditions (i.e., cardiovascular risk factors and diseases) and deaths. Additionally, calculated cardiovascular risk was assessed using the SCORE2 algorithm. Significant differences in baseline characteristics emerged between participants with and without tinnitus, with the former exhibiting advanced age, male predominance, and a higher prevalence of cardiovascular risk factors and diseases. Tinnitus displayed associations with various prevalent cardiovascular diseases including atrial fibrillation (odds ratio 1.48, 95% confidence interval 1.11-1.96), peripheral artery disease (1.43, 1.05-1.95), coronary artery disease (1.49, 1.09-2.04), and any cardiovascular disease (1.31, 1.11-1.56), persisting even after adjustments for demographic, socioeconomic, and cardiovascular risk factors. While crude associations with several prevalent cardiovascular risk factors were observed, these associations diminished upon comprehensive adjustment. Tinnitus presence was associated with elevated 10-year cardiovascular disease risk (incidence rate ratio 1.11, 1.09-1.13), as indicated by higher SCORE 2 values, yet did not predict all-cause mortality risk.

CONCLUSIONS

In the present study, tinnitus was associated with prevalent cardiovascular disease. However, no association with cardiovascular risk factors and mortality was found.

Risk Stratification for Cardiovascular Disease: A Comparative Analysis of Cluster Analysis and Traditional Prediction Models

AIM

Primary prevention of cardiovascular disease (CVD) relies on effective risk stratification to guide interventions. Current models, primarily developed using regression analysis, can lead to inaccurate estimates when applied to external populations. This study evaluates the utility of cluster analysis as an alternative method for developing CVD risk stratification models, comparing its performance with established CVD risk prediction models.

METHODS

Using data from 3,416 individuals (mean age of 66 years and no prior CVD) followed for an average of 5.2 years for incidence of CVD, we developed a risk stratification model using cluster analysis based on established CVD risk factors. We compared our model to the Systematic Coronary Risk Evaluation (SCORE2), the Pooled Cohort Equations (PCE) and the Predicting Risk of Cardiovascular Disease Events (PREVENT) models. We used Poisson and Cox regression to compare CVD risk between risk categories in each model. Predictive accuracy of the models was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and C-statistic.

RESULTS

During the study, 161 CVD events were detected. The high-risk cluster had a sensitivity of 59.0%, a PPV of 7.5% a specificity of 64.2% and NPV of 96.9% to predict CVD. Compared to the high-risk groups of the SCORE2, PCE and PREVENT, the high-risk cluster had a high sensitivity and NPV, but a low specificity and PPV. No statistically significant differences were found in C-statistic between models.

CONCLUSIONS

Cluster analysis performed comparably to existing models and identified a larger high-risk group that included more individuals who developed CVD, though with more false positives. Further studies in larger, diverse cohorts are needed to validate the clinical utility of cluster analysis in CVD risk stratification.

Early-onset or Premature Coronary Artery Disease

The aim of this review was to examine the literature regarding younger individuals without classical risk factors for atherosclerosis who develop coronary artery disease (CAD) prematurely at an early age. An extensive literature review was undertaken in Pubmed, Scopus, and Google Scholar regarding early-onset or premature atherosclerosis, CAD, its diagnosis, management, and prophylaxis. There are individuals of both genders, particularly in the younger age group of 20-40 years of age, who lack the traditional/ classical risk factors and still develop CAD and other manifestations of atherosclerosis. Even the 10-year age gap in manifesting CAD that is noted between women and men ascribable to a cardioprotective effect of sex hormones may not be noted under these circumstances. This indicates that the risk profile differs in young patients with nonclassical atherosclerotic risk factors, and factors such as genetics, inflammation, thrombosis, psychosocial, environmental, and other parameters play an important role in atherosclerosis and other mechanisms that lead to CAD in younger individuals. These patients are at risk of major adverse cardiac events, which determine their prognosis. Unfortunately, current major guidelines do not acknowledge that many patients who manifest premature CAD are at high risk, and as a consequence, many of these patients may not be receiving guideline-directed hypolipidemic and other therapies before they present with symptoms of CAD. Caretakers need to be more vigilant in offering efficacious screening and strategies of prevention for early-onset or premature CAD to younger individuals.

RiskPath: Explainable deep learning for multistep biomedical prediction in longitudinal data

Many diseases are the end outcomes of multifactorial risks that interact and increment over months or years. Timeseries AI methods have attracted increasing interest given their ability to operate on native timeseries data to predict disease outcomes. Instantiating such models in risk stratification tools has proceeded more slowly, in part limited by factors such as structural complexity, model size and explainability. Here, we present RiskPath, an explainable AI toolbox that offers advanced timeseries methods and additional functionality relevant to risk stratification use cases in classic and emerging longitudinal cohorts. Theoretically-informed optimization is integrated in prediction to specify optimal model topology or explore performance-complexity tradeoffs. Accompanying modules allow the user to map the changing importance of predictors over the disease course, visualize the most important antecedent time epochs contributing to disease risk or remove predictors to construct compact models for clinical applications with minimal performance impact.

Adding ethnicity to cardiovascular risk prediction: External validation and model updating of SCORE2 using data from the HELIUS population cohort

BACKGROUND

Current prediction models for mainland Europe do not include ethnicity, despite ethnic disparities in cardiovascular disease (CVD) risk. SCORE2 performance was evaluated across the largest ethnic groups in the Netherlands and ethnic backgrounds were added to the model.

METHODS

11,614 participants, aged between 40 and 70 years without CVD, from the population-based multi-ethnic HELIUS study were included. Fine and Gray models were used to calculate sub-distribution hazard ratios (SHR) for South-Asian Surinamese, African Surinamese, Ghanaian, Turkish and Moroccan origin groups, representing their CVD risk relative to the Dutch group, on top of individual SCORE2 risk predictions. Model performance was evaluated by discrimination, calibration and net reclassification index (NRI).

RESULTS

Overall, 274 fatal and non-fatal CVD events, and 146 non-cardiovascular deaths were observed during a median of 7.8 years follow-up (IQR 6.8-8.8). SHRs for CVD events were 1.86 (95 % CI 1.31-2.65) for the South-Asian Surinamese, 1.09 (95 % CI 0.76-1.56) for the African-Surinamese, 1.48 (95 % CI 0.94-2.31) for the Ghanaian, 1.63 (95 % CI 1.09-2.44) for the Turkish, and 0.67 (95 % CI 0.39-1.18) for the Moroccan origin groups. Adding ethnicity to SCORE2 yielded comparable calibration and discrimination [0.764 (95 % CI 0.735-0.792) vs. 0.769 (95 % CI 0.740-0.797)]. The NRI for adding ethnicity to SCORE2 was 0.24 (95 % CI 0.18-0.31) for events and - 0.12 (95 % CI -0.13-0.12) for non-events.

CONCLUSIONS

Adding ethnicity to the SCORE2 risk prediction model in a middle-aged, multi-ethnic Dutch population did not improve overall discrimination but improved risk classification, potentially helping to address CVD disparities through timely treatment.

Green space visits among Turkish and South Asian Surinamese women with a high cardiometabolic risk living in disadvantaged neighborhoods in the Netherlands: motives, means and prerequisites

BACKGROUND

The use of urban green spaces differs by social characteristics, including gender, ethnicity, and socioeconomic position. We examined motives, means and prerequisites to visit green space of marginalised populations with high cardiometabolic risk in the Netherlands, namely women with a Turkish or South Asian Surinamese background residing in disadvantaged neighbourhoods.

METHODS

We conducted six focus group discussions in two Dutch cities. The study was performed in collaboration with social workers from the local communities with similar ethnic backgrounds as the participants. A thematic analysis was carried out.

RESULTS

Sixteen Turkish women and 30 South Asian Surinamese women participated. Motives, means and prerequisites that emerged covered four themes: social, personal, environmental characteristics and undertaking activities. Socializing was an important motive to visit green space. Personal motives mainly consisted of positive effects on mental and physical well-being. Activities undertaken in green space were often a means to socialize or improve well-being. Many environmental factors, including safety, aesthetics, and (sanitary) facilities, influenced motivation to visit green space. Except for environmental characteristics, motives, means and prerequisites largely overlapped between ethnic groups. There were notable interactions between the themes.

CONCLUSION

Motives, means and prerequisites to visit green space of women with a Turkish or South Asian Surinamese background who live in disadvantaged neighborhoods span multiple interacting themes. Future studies examining the relationship between green space and health should consider interactions between motives, means, prerequisites and ethnicity. The possibility of expanding the multifunctionality of green spaces to provide marginalized populations with more equitable access and activities should be further explored.

Aggregation of cardiovascular risk factors in a cohort of 40-year-olds participating in a population-based health screening program in Sweden

BACKGROUND

It is important to identify and evaluate cardiovascular risk factors at an early stage to address them accordingly. Among the younger population, the metabolic syndrome is less common than in older ages. However, each separate metabolic risk factor still has an additive effect on cardiovascular risk factor burden. Non-metabolic risk factors that occur in the younger population include family history, smoking, psychological distress and socioeconomic vulnerability. In 2021 a voluntary health intervention program was introduced in an urban area in Sweden where a cohort of 40-year-olds was invited for cardiovascular risk identification. The aim of this study was to identify how cardiovascular risk factors tend to aggregate in individuals participating in a voluntary health screening program and how the metabolic risk factors associate with non-metabolic cardiovascular risk factors.

METHODS

This was a cross-sectional study with 1831 participants. Data from questionnaires and baseline measurements were used to calculate the prevalence of metabolic- (blood pressure, lipids, fasting plasma glucose, BMI, waist-hip ratio) and non-metabolic risk factors (family history of CVD, smoking, psychological distress, socioeconomic vulnerability) for CVD. SCORE2 was calculated according to the algorithm provided by the SCORE2 working group and ESC (European Society of Cardiology) Cardiovascular Risk Collaboration. Associations among each of the metabolic risk factors and non-metabolic risk factors were estimated using logistic regression and presented as odds ratios (ORs) with 95% confidence intervals (CIs).

RESULTS

More than half of the study population had at least one metabolic risk factor, and more than 1/3 was considered to be suffering from psychological distress. Furthermore, obesity or central obesity demonstrated individual associations with all of the non-metabolic risk factors in the study; smoking (1.49; 1.32-2.63), family history of CVD (1.41; 1.14-1.73), socioeconomic vulnerability (1.60; 1.24-2.07), and psychological distress (1.40; 1.14-1.72). According to SCORE2 25% of the men were at moderate risk (2.5-7.5%) of developing a cardiovascular event within 5-10 years, but only 2% of the women.

CONCLUSIONS

Obesity/central obesity should be a prioritized target in health screening programs. The non-metabolic risk factors, socioeconomic vulnerability, and psychological distress should not be ignored and addressed with adequate guidance to create health equity.

Computed tomography and coronary artery calcium score for screening of coronary artery disease and cardiovascular risk management in asymptomatic individuals

Several risk prediction models exist to predict atherosclerotic cardiovascular disease in asymptomatic individuals, but systematic reviews have generally found these models to be of limited utility. The coronary artery calcium score (CACS) offers an improvement in risk prediction, yet its role remains contentious. Notably, its negative predictive value has a high ability to rule out clinically relevant atherosclerotic cardiovascular disease. Nonetheless, CACS 0 does not permanently reclassify to a lower cardiovascular risk and periodic reassessment every 5 to 10 years remains necessary. Conversely, elevated CACS (> 100 or > 75th percentile adjusted for age, sex and ethnicity) can reclassify intermediate-risk individuals to a high risk, benefiting from preventive medication. The forthcoming update to the Dutch cardiovascular risk management guideline intends to re-position CACS for cardiovascular risk assessment as such in asymptomatic individuals. Beyond CACS as a single number, several guidelines recommend coronary CT angiography (CCTA), which provides additional information about luminal stenosis and (high-risk) plaque composition, as the first choice of test in symptomatic patients and high-risk patients. Ongoing randomised studies will have to determine the value of atherosclerosis evaluation with CCTA for primary prevention in asymptomatic individuals.

Prediction of individual lifetime cardiovascular risk and potential treatment benefit: development and recalibration of the LIFE-CVD2 model to four European risk regions

AIMS

The 2021 European Society of Cardiology prevention guidelines recommend the use of (lifetime) risk prediction models to aid decisions regarding initiation of prevention. We aimed to update and systematically recalibrate the LIFEtime-perspective CardioVascular Disease (LIFE-CVD) model to four European risk regions for the estimation of lifetime CVD risk for apparently healthy individuals.

METHODS AND RESULTS

The updated LIFE-CVD (i.e. LIFE-CVD2) models were derived using individual participant data from 44 cohorts in 13 countries (687 135 individuals without established CVD, 30 939 CVD events in median 10.7 years of follow-up). LIFE-CVD2 uses sex-specific functions to estimate the lifetime risk of fatal and non-fatal CVD events with adjustment for the competing risk of non-CVD death and is systematically recalibrated to four distinct European risk regions. The updated models showed good discrimination in external validation among 1 657 707 individuals (61 311 CVD events) from eight additional European cohorts in seven countries, with a pooled C-index of 0.795 (95% confidence interval 0.767-0.822). Predicted and observed CVD event risks were well calibrated in population-wide electronic health records data in the UK (Clinical Practice Research Datalink) and the Netherlands (Extramural LUMC Academic Network). When using LIFE-CVD2 to estimate potential gain in CVD-free life expectancy from preventive therapy, projections varied by risk region reflecting important regional differences in absolute lifetime risk. For example, a 50-year-old smoking woman with a systolic blood pressure (SBP) of 140 mmHg was estimated to gain 0.9 years in the low-risk region vs. 1.6 years in the very high-risk region from lifelong 10 mmHg SBP reduction. The benefit of smoking cessation for this individual ranged from 3.6 years in the low-risk region to 4.8 years in the very high-risk region.

CONCLUSION

By taking into account geographical differences in CVD incidence using contemporary representative data sources, the recalibrated LIFE-CVD2 model provides a more accurate tool for the prediction of lifetime risk and CVD-free life expectancy for individuals without previous CVD, facilitating shared decision-making for cardiovascular prevention as recommended by 2021 European guidelines.

Deep Inspiration Breath Hold in Left-Sided Breast Radiotherapy: A Balance Between Side Effects and Costs

Background

Deep inspiration breath hold (DIBH) is an effective technique for reducing heart exposure during radiotherapy for left-sided breast cancer. Despite its benefits, cost considerations and its impact on workflow remain significant barriers to widespread adoption.

Objectives

This study aimed to assess the cost-effectiveness of DIBH and compare its operational, financial, and clinical outcomes with free breathing (FB) in breast cancer treatment.

Methods

Treatment plans for 100 patients with left-sided breast cancer were generated using both DIBH and FB techniques. Dosimetric data, including the average mean heart dose, were calculated for each technique and used to estimate the cardiotoxicity of radiotherapy. A state-transition microsimulation model based on SCORE2 (Systematic Coronary Risk Evaluation) algorithms projected the effects of DIBH on cardiovascular outcomes and quality-adjusted life-years (QALYs). Costs were calculated from a provider perspective using time-driven activity-based costing, applying a willingness-to-pay threshold of €40,000 for cost-effectiveness assessment. A discrete event simulation model assessed the impacts of DIBH vs FB on throughput and waiting times in the radiotherapy workflow.

Results

In the base case scenario, DIBH was associated with an absolute risk reduction of 1.72% (95% CI: 1.67%-1.76%) in total cardiovascular events and 0.69% (95% CI: 0.67%-0.72%) in fatal cardiovascular events over 20 years. Additionally, DIBH was estimated to provide an incremental 0.04 QALYs (95% CI: 0.05-0.05) per left-sided breast cancer patient over the same time period. However, DIBH increased treatment times, reducing maximum achievable throughput by 12.48% (95% CI: 12.36%-12.75%) and increasing costs by €617 per left-sided breast cancer patient (95% CI: €615-€619). The incremental cost-effectiveness ratio was €14,023 per QALY.

Conclusions

Despite time investments, DIBH is cost-effective in the Belgian population. The growing adoption of DIBH may benefit long-term cardiovascular health in breast cancer survivors.

Antihypertensive medication classes and risk of incident dementia in primary care patients: a longitudinal cohort study in the Netherlands

Background

Hypertension is a modifiable risk factor for dementia affecting over 70% of individuals older than 60. Lowering dementia risk through preferential treatment with antihypertensive medication (AHM) classes that are otherwise equivalent in indication could offer a cost-effective, safe, and accessible approach to reducing dementia incidence globally. Certain AHM-classes have been associated with lower dementia risk, potentially attributable to angiotensin-II-receptor (Ang-II) stimulating properties. Previous study results have been inconclusive, possibly due to heterogeneous methodology and limited power. We aimed to comprehensively investigate associations between AHM (sub-)classes and dementia risk using large-scale continuous, real-world prescription and outcome data from primary care.

Methods

We used data from three Dutch General Practice Registration Networks. Primary endpoints were clinical diagnosis of incident all-cause dementia and mortality. Using Cox regression analysis with time-dependent covariates, we compared the use of angiotensin-converting enzyme inhibitors (ACEi) to angiotensin receptor blockers (ARBs), beta blockers, calcium channel blockers (CCBs), and diuretics; and Ang-II-stimulating- to Ang-II-inhibiting AHM.

Findings

Of 133,355 AHM-using participants, 5877 (4.4%) developed dementia, and 14,079 (10.6%) died during a median follow-up of 7.6 [interquartile range = 4.1-11.0] years. Compared to ACEi, ARBs [HR = 0.86 (95% CI = 0.80-0.92)], beta blockers [HR = 0.81 (95% CI = 0.75-0.87)], CCBs [HR = 0.77 (95% CI = 0.71-0.84)], and diuretics [HR = 0.65 (95% CI = 0.61-0.70)] were associated with significantly lower dementia risks. Regarding competing risk of death, beta blockers [HR = 1.21 (95% CI = 1.15-1.27)] and diuretics [HR = 1.69 (95% CI = 1.60-1.78)] were associated with higher, CCBs with similar, and ARBs with lower [HR = 0.83 (95% CI = 0.80-0.87)] mortality risk. Dementia [HR = 0.88 (95% CI = 0.82-0.95)] and mortality risk [HR = 0.86 (95% CI = 0.82-0.91)] were lower for Ang-II-stimulating versus Ang-II-inhibiting AHM. There were no interactions with sex, diabetes, cardiovascular disease, and number of AHM used.

Interpretation

Among patients receiving AHM, ARBs, CCBs, and Ang-II-stimulating AHM were associated with lower dementia risk, without excess mortality explaining these results. Extensive subgroup and sensitivity analyses suggested that confounding by indication did not importantly influence our findings. Dementia risk may be influenced by AHM-classes' angiotensin-II-receptor stimulating properties. An RCT comparing BP treatment with different AHM classes with dementia as outcome is warranted.

Funding

Netherlands Organisation for Health, Research and Development (ZonMw); Stoffels-Hornstra Foundation.

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

AIMS

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. This study aims to assess discrimination, calibration, and clinical utility of low-risk SCORE2 and SCORE2-OP.

METHODS AND RESULTS

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). For SCORE2, 19 560 individuals (57% women) had 10-year CVD risk estimates of 3.7% [95% confidence interval (CI) 3.6-3.7] vs. 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. Systematic Coronary Risk Evaluation 2-Older Persons in 3113 individuals (58% women) predicted 10-year CVD events in 10.2% (95% CI 10.1-10.3) vs. 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. Decision curve analysis 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.

Volatilome: A Novel Tool for Risk Scoring in Ischemic Heart Disease

Developing a novel risk score for accurate assessment of cardiovascular disease (CVD) morbidity and mortality is an urgent need in terms of early prevention and diagnosis and, thereafter, management, particularly of ischemic heart disease. The currently used scores for the evaluation of cardiovascular disease based on the classical risk factors suffer from severe limitations, including inaccurate predictive values. Therefore, we suggest adding a novel non-classical risk factor, including the level of specific exhaled volatile organic compounds that are associated with ischemic heart disease, to the SCORE2 and SCORE2-OP algorithms. Adding these nonclassical risk factors can be used together with the classical risk factors (gender, smoking, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, diabetes mellitus, arterial hypertension, ethnicity, etc.) to develop a new algorithm and further program to be used widely.

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

Aims

Existing electronic health records (EHRs) often consist of abundant but irregular longitudinal measurements of risk factors. In this study, we aim to leverage such data to improve the risk prediction of atherosclerotic cardiovascular disease (ASCVD) by applying machine learning (ML) algorithms, which can allow automatic screening of the population.

Methods and results

A total of 215 744 Chinese adults aged between 40 and 79 without a history of cardiovascular disease were included (6081 cases) from an EHR-based longitudinal cohort study. To allow interpretability of the model, the predictors of demographic characteristics, medication treatment, and repeatedly measured records of lipids, glycaemia, 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) algorithm and Least Absolute Shrinkage and Selection Operator (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 a significantly higher C-statistic of 0.792, (the differences in the C-statistics: 0.011, 0.006-0.017, P < 0.001), with similar results reported for LASSO regression (the differences in the 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 risk distribution of the ML algorithms differed from that of the conventional model. The net reclassification improvement rates of XGBoost and LASSO over the Cox model were 3.9% (1.4-6.4%) and 2.8% (0.7-4.9%), respectively.

Conclusion

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.

Algorithmic fairness in cardiovascular disease risk prediction: overcoming inequalities

The main purpose of prognostic risk prediction models is to identify individuals who are at risk of disease, to enable early intervention. Current prognostic cardiovascular risk prediction models, such as the Systematic COronary Risk Evaluation (SCORE2) and the SCORE2-Older Persons (SCORE2-OP) models, which represent the clinically used gold standard in assessing patient risk for major cardiovascular events in the European Union (EU), generally overlook socioeconomic determinants, leading to disparities in risk prediction and resource allocation. A central recommendation of this article is the explicit inclusion of individual-level socioeconomic determinants of cardiovascular disease in risk prediction models. The question of whether prognostic risk prediction models can promote health equity remains to be answered through experimental research, potential clinical implementation and public health analysis. This paper introduces four distinct fairness concepts in cardiovascular disease prediction and their potential to narrow existing disparities in cardiometabolic health.