Prediction models for cardiovascular disease risk in the general population: systematic review

A dynamic probabilistic model of the onset and interaction of cardio-metabolic comorbidities on an ageing adult population

Comorbidity is widespread in the ageing population, implying multiple and complex medical needs for individuals and a public health burden. Determining risk factors and predicting comorbidity development can help identify at-risk subjects and design prevention strategies. Using socio-demographic and clinical data from approximately 11,000 subjects monitored over 11 years in the English Longitudinal Study of Ageing, we develop a dynamic Bayesian network (DBN) to model the onset and interaction of three cardio-metabolic comorbidities, namely type 2 diabetes (T2D), hypertension, and heart problems. The DBN allows us to identify risk factors for developing each morbidity, simulate ageing progression over time, and stratify the population based on the risk of outcome occurrence. By applying hierarchical agglomerative clustering to the simulated, dynamic risk of experiencing morbidities, we identified patients with similar risk patterns and the variables contributing to their discrimination. The network reveals a direct joint effect of biomarkers and lifestyle on outcomes over time, such as the impact of fasting glucose, HbA1c, and BMI on T2D development. Mediated cross-relationships between comorbidities also emerge, showcasing the interconnected nature of these health issues. The model presents good calibration and discrimination ability, particularly in predicting the onset of T2D (iAUC-ROC = 0.828, iAUC-PR = 0.294) and survival (iAUC-ROC = 0.827, iAUC-PR = 0.311). Stratification analysis unveils two distinct clusters for all comorbidities, effectively discriminated by variables like HbA1c for T2D and age at baseline for heart problems. The developed DBN constitutes an effective, highly-explainable predictive risk tool for simulating and stratifying the dynamic risk of developing cardio-metabolic comorbidities. Its use could help identify the effects of risk factors and develop health policies that prevent the occurrence of comorbidities.

A meta-analysis of diabetes risk prediction models applied to prediabetes screening

AIM

To provide a systematic overview of diabetes risk prediction models used for prediabetes screening to promote primary prevention of diabetes.

METHODS

The Cochrane, PubMed, Embase, Web of Science and China National Knowledge Infrastructure (CNKI) databases were searched for a comprehensive search period of 30 August 30, 2023, and studies involving diabetes prediction models for screening prediabetes risk were included in the search. The Quality Assessment Checklist for Diagnostic Studies (QUADAS-2) tool was used for risk of bias assessment and Stata and R software were used to pool model effect sizes.

RESULTS

A total of 29 375 articles were screened, and finally 20 models from 24 studies were included in the systematic review. The most common predictors were age, body mass index, family history of diabetes, history of hypertension, and physical activity. Regarding the indicators of model prediction performance, discrimination and calibration were only reported in 79.2% and 4.2% of studies, respectively, resulting in significant heterogeneity in model prediction results, which may be related to differences between model predictor combinations and lack of important methodological information.

CONCLUSIONS

Numerous models are used to predict diabetes, and as there is an association between prediabetes and diabetes, researchers have also used such models for screening the prediabetic population. Although it is a new clinical practice to explore, differences in glycaemic metabolic profiles, potential complications, and methods of intervention between the two populations cannot be ignored, and such differences have led to poor validity and accuracy of the models. Therefore, there is no recommended optimal model, and it is not recommended to use existing models for risk identification in alternative populations; future studies should focus on improving the clinical relevance and predictive performance of existing models.

Comparison of prediction models for cardiovascular and mortality risk in people with type 2 diabetes: An external validation in 23 685 adults included in the UK Biobank

AIMS

To validate cardiovascular risk prediction models for individuals with diabetes using the UK Biobank in order to assess their applicability.

METHODS

We externally validated 19 cardiovascular risk scores from seven risk prediction models (Chang et al., Framingham, University of Hong Kong-Singapore [HKU-SG], Li et al, RECODe [risk equations for complications of type 2 diabetes], SCORE [Systematic Coronary Risk Evaluation] and the UK Prospective Diabetes Study Outcomes Model 2 [UKPDS OM2]), identified from systematic reviews, using UK Biobank data from 2006 to 2021 (n = 23 685; participant age 40-71 years, 63.5% male). We evaluated performance by assessing the discrimination and calibration of the models for the endpoints of mortality, cardiovascular mortality, congestive heart failure, myocardial infarction, stroke, and ischaemic heart disease.

RESULTS

Over a total of 269 430 person-years of follow-up (median 11.89 years), the models showed low-to-moderate discrimination performance on external validation (concordance indices [c-indices] 0.50-0.71). Most models had low calibration with overprediction of the observed risk. RECODe outperformed other models across four comparable endpoints for discrimination: all-cause mortality (c-index 0.67, 95% confidence interval [CI] 0.65-0.69), congestive heart failure (c-index 0.71, 95% CI 0.69-0.72), myocardial infarction (c-index 0.67, 95% CI 0.65-0.68); and stroke (c-index 0.65, 95% CI 0.62-0.68), and for calibration (except for all-cause mortality). The UKPDS OM2 had comparable performance to RECODe for all-cause mortality (c-index 0.67, 95% CI 0.66-0.69) and cardiovascular mortality (c-index 0.71, 95% CI 0.70-0.73), but worse performance for other outcomes. The models performed better for younger participants and somewhat better for non-White ethnicities. Models developed from non-Western datasets showed worse performance in our UK-based validation set.

CONCLUSIONS

The RECODe model led to better risk estimations in this predominantly White European population. Further validation is needed in non-Western populations to assess generalizability to other populations.

Age-dependent association of central blood pressure with cardiovascular outcomes: a cohort study involving 34 289 participants using the UK biobank

BACKGROUND

It remained unclear whether central blood pressures (BP) was more closely associated with cardiovascular disease (CVD) than brachial BP in different age groups.

OBJECTIVES

To investigate the age-stratified association of CVD with brachial and central BPs, and to evaluate corresponding improvement in model performance.

METHODS

This cohort study included 34 289 adults without baseline CVD from the UK Biobank dataset. Participants were categorized into middle-aged and older aged groups using the cut-off of age 65 years. The primary endpoint was a composite cardiovascular outcome consisting of cardiovascular mortality combined with nonfatal coronary events, heart failure and stroke. Multivariable-adjusted hazard ratios expressed CVD risks associated with BP increments of 10 mmHg. Akaike Information Criteria (AIC) was used for model comparisons.

RESULTS

In both groups, CVD events were associated with brachial or central SBP ( P  ≤ 0.002). Model fit was better for central SBP in middle-aged adults (AIC 4427.2 vs. 4429.5), but model fit was better for brachial SBP in older adults (AIC 10 246.7 vs. 10 247.1). Central SBP remained significantly associated to CVD events [hazard ratio = 1.05; 95% confidence interval (CI) 1.0-1.1] and improved model fit (AIC = 4426.6) after adjustment of brachial SBP only in the middle-aged adults. These results were consistent for pulse pressure (PP).

CONCLUSION

In middle-aged adults, higher central BPs were associated with greater risks of CVD events, even after adjusting for brachial BP indexes. For older adults, the superiority of central BP was not observed. Additional trials with adequate follow-up time will confirm the role of central BP in estimating CVD risk for middle-aged individuals.

Development and validation of risk prediction model for recurrent cardiovascular events among Chinese: the Personalized CARdiovascular DIsease risk Assessment for Chinese model

Aims

Cardiovascular disease (CVD) is a leading cause of mortality, especially in developing countries. This study aimed to develop and validate a CVD risk prediction model, Personalized CARdiovascular DIsease risk Assessment for Chinese (P-CARDIAC), for recurrent cardiovascular events using machine learning technique.

Methods and results

Three cohorts of Chinese patients with established CVD were included if they had used any of the public healthcare services provided by the Hong Kong Hospital Authority (HA) since 2004 and categorized by their geographical locations. The 10-year CVD outcome was a composite of diagnostic or procedure codes with specific International Classification of Diseases, Ninth Revision, Clinical Modification. Multivariate imputation with chained equations and XGBoost were applied for the model development. The comparison with Thrombolysis in Myocardial Infarction Risk Score for Secondary Prevention (TRS-2°P) and Secondary Manifestations of ARTerial disease (SMART2) used the validation cohorts with 1000 bootstrap replicates. A total of 48 799, 119 672 and 140 533 patients were included in the derivation and validation cohorts, respectively. A list of 125 risk variables were used to make predictions on CVD risk, of which 8 classes of CVD-related drugs were considered interactive covariates. Model performance in the derivation cohort showed satisfying discrimination and calibration with a C statistic of 0.69. Internal validation showed good discrimination and calibration performance with C statistic over 0.6. The P-CARDIAC also showed better performance than TRS-2°P and SMART2.

Conclusion

Compared with other risk scores, the P-CARDIAC enables to identify unique patterns of Chinese patients with established CVD. We anticipate that the P-CARDIAC can be applied in various settings to prevent recurrent CVD events, thus reducing the related healthcare burden.

Comparison of the performance of cardiovascular risk prediction tools in rural India: the Rishi Valley Prospective Cohort Study

AIMS

We compared the performance of cardiovascular risk prediction tools in rural India.

METHODS AND RESULTS

We applied the World Health Organization Risk Score (WHO-RS) tools, Australian Risk Score (ARS), and Global risk (Globorisk) prediction tools to participants aged 40-74 years, without prior cardiovascular disease, in the Rishi Valley Prospective Cohort Study, Andhra Pradesh, India. Cardiovascular events during the 5-year follow-up period were identified by verbal autopsy (fatal events) or self-report (non-fatal events). The predictive performance of each tool was assessed by discrimination and calibration. Sensitivity and specificity of each tool for identifying high-risk individuals were assessed using a risk score cut-off of 10% alone or this 10% cut-off plus clinical risk criteria of diabetes in those aged >60 years, high blood pressure, or high cholesterol. Among 2333 participants (10 731 person-years of follow-up), 102 participants developed a cardiovascular event. The 5-year observed risk was 4.4% (95% confidence interval: 3.6-5.3). The WHO-RS tools underestimated cardiovascular risk but the ARS overestimated risk, particularly in men. Both the laboratory-based (C-statistic: 0.68 and χ2: 26.5, P = 0.003) and non-laboratory-based (C-statistic: 0.69 and χ2: 20.29, P = 0.003) Globorisk tools showed relatively good discrimination and agreement. Addition of clinical criteria to a 10% risk score cut-off improved the diagnostic accuracy of all tools.

CONCLUSION

Cardiovascular risk prediction tools performed disparately in a setting of disadvantage in rural India, with the Globorisk performing best. Addition of clinical criteria to a 10% risk score cut-off aids assessment of risk of a cardiovascular event in rural India.

LAY SUMMARY

In a cohort of people without prior cardiovascular disease, tools used to predict the risk of cardiovascular events varied widely in their ability to accurately predict who would develop a cardiovascular event.The Globorisk, and to a lesser extent the ARS, tools could be appropriate for this setting in rural India.Adding clinical criteria, such as sustained high blood pressure, to a cut-off of 10% risk of a cardiovascular event within 5 years could improve identification of individuals who should be monitored closely and provided with appropriate preventive medications.

Validation of the European SCORE2 models in a Canadian primary care cohort

AIMS

Systematic Coronary Risk Evaluation Model 2 (SCORE2) was recently developed to predict atherosclerotic cardiovascular disease (ASCVD) in Europe. Whether these models could be used outside of Europe is not known. The objective of this study was to test the validity of SCORE2 in a large Canadian cohort.

METHODS AND RESULTS

A primary care cohort of persons with routinely collected electronic medical record data from 1 January 2010 to 31 December 2014, in Ontario, Canada, was used for validation. The SCORE2 models for younger persons (YP) were applied to 57 409 individuals aged 40-69 while the models for older persons (OPs) were applied to 9885 individuals 70-89 years of age. Five-year ASCVD predictions from both the uncalibrated and low-risk region recalibrated SCORE2 models were evaluated. The C-statistic for SCORE2-YP was 0.74 in women and 0.69 in men. The uncalibrated SCORE2-YP overestimated risk by 17% in women and underestimated by 2% in men. In contrast, the low-risk region recalibrated model demonstrated worse calibration, overestimating risk by 100% in women and 36% in men. The C-statistic for SCORE2-OP was 0.64 and 0.62 in older women and men, respectively. The uncalibrated SCORE2-OP overestimated risk by more than 100% in both sexes. The low-risk region recalibrated model demonstrated improved calibration but still overestimated risk by 60% in women and 13% in men.

CONCLUSION

The performance of SCORE2 to predict ASCVD risk in Canada varied by age group and depended on whether regional calibration was applied. This underscores the necessity for validation assessment of SCORE2 prior to implementation in new jurisdictions.

The global burden and risk factors of cardiovascular diseases in adolescent and young adults, 1990-2019

BACKGROUND

To provide details of the burden and the trend of the cardiovascular disease (CVD) and its risk factors in adolescent and young adults.

METHODS

Age-standardized rates (ASRs) of incidence, mortality and Disability-Adjusted Life Years (DALYs) were used to describe the burden of CVD in adolescents and young adults. Estimated Annual Percentage Changes (EAPCs) of ASRs were used to describe the trend from 1990 to 2019. Risk factors were calculated by Population Attributable Fractions (PAFs).

RESULTS

In 2019, the age-standardized incidence rate (ASIR), age-standardized mortality rate (ASMR) and age-standardized DALYs rate (ASDR) of CVD were 129.85 per 100 000 (95% Confidence interval (CI): 102.60, 160.31), 15.12 per 100 000 (95% CI: 13.89, 16.48) and 990.64 per 100 000 (95% CI: 911.06, 1076.46). The highest ASRs were seen in low sociodemographic index (SDI) and low-middle SDI regions. The burden was heavier in male and individuals aged 35-39. From 1990 to 2019, 72 (35.29%) countries showed an increasing trend of ASIR and more than 80% countries showed a downward trend in ASMR and ASDR. Rheumatic heart disease had the highest ASIR and Ischemic Heart Disease was the highest in both ASMR and ASDR. The main attributable risk factor for death and DALYs were high systolic blood pressure, high body-mass index and high LDL cholesterol.

CONCLUSIONS

The burden of CVD in adolescent and young adults is a significant global health challenge. It is crucial to take into account the disparities in SDI levels among countries, gender and age characteristics of the population, primary types of CVD, and the attributable risk factors when formulating and implementing prevention strategies.

Debate: CAMHS will be at the forefront of the next generation of psychosis risk models, but further integration with early intervention psychosis services is needed to realise this potential: Re Debate: Prevention of psychosis in adolescents - does CAMHS have a role?

The detection of psychosis and its prodrome have unique considerations in a child and adolescent population. Young people attending CAMHS are already a high-risk group, which confers significant limitations in applying the current clinical high-risk (CHR) model. This has catalysed calls for a transdiagnostic approach to psychosis risk prediction, but without a clear pathway forward. We contribute to the debate opened by Salazar de Pablo and Arango (2023, Child and Adolescent Mental Health) on the role of CAMHS in this initiative. CAMHS have a key role in developing comprehensive longitudinal datasets to inform risk models. Closer integration with early intervention in psychosis (EIP) services will be needed to realise this potential. This integration is also required to reliably detect prodromes and emerging psychosis in young people. Where there is robust evidence to support prevention initiatives, we should proceed with their implementation, even in the absence of enhanced risk models.

Preeclampsia-Associated Cardiovascular Risk Factors 6 Months and 2 Years After Pregnancy: The P4 Study

BACKGROUND

Increased cardiovascular risk following preeclampsia is well established and there are signs of early cardiovascular aging 6 months postpartum. This study assessed whether blood pressure (BP) and other cardiovascular measures are abnormal 2 years postpartum in the same cohort to determine ongoing risk markers.

METHODS

Six months and 2 years postpartum, BP was measured using sphygmomanometry, 24-hour ambulatory BP monitoring, and noninvasive central BP. Anthropometric measures, blood, and urine biochemistry were performed. Cross-sectional comparisons between preeclampsia and normotensive pregnancy (NP) groups and longitudinal comparisons within each group were made at 6 months and 2 years.

RESULTS

Two years postpartum, 129 NP, and 52 preeclampsia women were studied who also had 6 months measures. At both time points, preeclampsia group had significantly higher BP (office BP 2 years, 112±12/72±8 versus 104±9/67±7 mm Hg NP; [P<0.001]; mean ambulatory BP monitoring 116±9/73±8 versus 106±8/67±6 mm Hg NP; [P<0.001]). No significant BP changes noted 6 months to 2 years within either group. Office BP thresholds of 140 mm Hg systolic and 90 mm Hg diastolic classified 2% preeclampsia and 0% NP at 2 years. American Heart Association 2017 criteria (above normal, >120/80 mm Hg) classified 25% versus 8% (P<0.002), as did our reference range threshold of 122/79 mm Hg. American Heart Association criteria classified 60% post-preeclampsia versus 16% after NP with above-normal ambulatory BP monitoring (P<0.001). Other cardiovascular risk markers more common 2 years post-preeclampsia included higher body mass index (median 26.6 versus 23.1, P=0.003) and insulin resistance.

CONCLUSIONS

After preeclampsia, women have significantly higher BP 6 months and 2 years postpartum, and have higher body mass index and insulin-resistance scores, increasing their future cardiovascular risk. Regular cardiovascular risk screening should be implemented for all who have experienced preeclampsia.

Risk of cardiovascular death in patients with hepatocellular carcinoma based on the Fine-Gray model

BACKGROUND

Hepatocellular carcinoma (HCC) is one of the most common types of cancers worldwide, ranking fifth among men and seventh among women, resulting in more than 7 million deaths annually. With the development of medical technology, the 5-year survival rate of HCC patients can be increased to 70%. However, HCC patients are often at increased risk of cardiovascular disease (CVD) death due to exposure to potentially cardiotoxic treatments compared with non-HCC patients. Moreover, CVD and cancer have become major disease burdens worldwide. Thus, further research is needed to lessen the risk of CVD death in HCC patient survivors.

AIM

To determine the independent risk factors for CVD death in HCC patients and predict cardiovascular mortality (CVM) in HCC patients.

METHODS

This study was conducted on the basis of the Surveillance, Epidemiology, and End Results database and included HCC patients with a diagnosis period from 2010 to 2015. The independent risk factors were identified using the Fine-Gray model. A nomograph was constructed to predict the CVM in HCC patients. The nomograph performance was measured using Harrell's concordance index (C-index), calibration curve, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC) value. Moreover, the net benefit was estimated via decision curve analysis (DCA).

RESULTS

The study included 21545 HCC patients, of whom 619 died of CVD. Age (< 60) [1.981 (1.573-2.496), P < 0.001], marital status (married) [unmarried: 1.370 (1.076-1.745), P = 0.011], alpha fetoprotein (normal) [0.778 (0.640-0.946), P = 0.012], tumor size (≤ 2 cm) [(2, 5] cm: 1.420 (1.060-1.903), P = 0.019; > 5 cm: 2.090 (1.543-2.830), P < 0.001], surgery (no) [0.376 (0.297-0.476), P < 0.001], and chemotherapy(none/unknown) [0.578 (0.472-0.709), P < 0.001] were independent risk factors for CVD death in HCC patients. The discrimination and calibration of the nomograph were better. The C-index values for the training and validation sets were 0.736 and 0.665, respectively. The AUC values of the ROC curves at 2, 4, and 6 years were 0.702, 0.725, 0.740 in the training set and 0.697, 0.710, 0.744 in the validation set, respectively. The calibration curves showed that the predicted probabilities of the CVM prediction model in the training set vs the validation set were largely consistent with the actual probabilities. DCA demonstrated that the prediction model has a high net benefit.

CONCLUSION

Risk factors for CVD death in HCC patients were investigated for the first time. The nomograph served as an important reference tool for relevant clinical management decisions.

Effects of message framing and risk perception on health communication for optimum cardiovascular disease primary prevention: a protocol for a multicenter randomized controlled study

Background

Although several guidelines for cardiovascular disease (CVD) management have highlighted the significance of primary prevention, the execution and adherence to lifestyle modifications and preventive medication interventions are insufficient in everyday clinical practice. The utilization of effective risk communication can assist individuals in shaping their perception of CVD risk, motivating them to make lifestyle changes, and increasing their willingness to engage with preventive medication, ultimately reducing their CVD risks and potential future events. However, there is limited evidence available regarding the optimal format and content of CVD risk communication.

Objective

The pilot study aims to elucidate the most effective risk communication strategy, utilizing message framing (gain-framed, loss-framed, or no-framed), for distinct subgroups of risk perception (under-perceived, over-perceived, and correctly-perceived CVD risk) through a multi-center randomized controlled trial design.

Methods

A multi-center 3 × 3 factorial, observer-blinded experimental design was conducted. The participants will be assigned into three message-framing arms randomly in a 1:1:1 ratio and will receive an 8-week intervention online. Participants are aged 20-80 years old and have a 10-year risk of absolute CVD risk of at least 5% (moderate risk or above). We plan to enroll 240 participants based on the sample calculation. The primary outcome is the CVD prevention behaviors and CVD absolute risk value. Data collection will occur at baseline, post-intervention, and 3-month follow-up.

Discussion

This experimental study will expect to determine the optimal matching strategy between risk perception subgroups and risk information format, and it has the potential to offer health providers in community or clinic settings a dependable and efficient health communication information template for conducting CVD risk management.Clinical trial registration: https://www.chictr.org.cn/bin/project/edit?pid=207811, ChiCTR2300076337.

Seasonally adjusted laboratory reference intervals to improve the performance of machine learning models for classification of cardiovascular diseases

BACKGROUND

Variation in laboratory healthcare data due to seasonal changes is a widely accepted phenomenon. Seasonal variation is generally not systematically accounted for in healthcare settings. This study applies a newly developed adjustment method for seasonal variation to analyze the effect seasonality has on machine learning model classification of diagnoses.

METHODS

Machine learning methods were trained and tested on ~ 22 million unique records from ~ 575,000 unique patients admitted to Danish hospitals. Four machine learning models (adaBoost, decision tree, neural net, and random forest) classifying 35 diseases of the circulatory system (ICD-10 diagnosis codes, chapter IX) were run before and after seasonal adjustment of 23 laboratory reference intervals (RIs). The effect of the adjustment was benchmarked via its contribution to machine learning models trained using hyperparameter optimization and assessed quantitatively using performance metrics (AUROC and AUPRC).

RESULTS

Seasonally adjusted RIs significantly improved cardiovascular disease classification in 24 of the 35 tested cases when using neural net models. Features with the highest average feature importance (via SHAP explainability) across all disease models were sex, C- reactive protein, and estimated glomerular filtration. Classification of diseases of the vessels, such as thrombotic diseases and other atherosclerotic diseases consistently improved after seasonal adjustment.

CONCLUSIONS

As data volumes increase and data-driven methods are becoming more advanced, it is essential to improve data quality at the pre-processing level. This study presents a method that makes it feasible to introduce seasonally adjusted RIs into the clinical research space in any disease domain. Seasonally adjusted RIs generally improve diagnoses classification and thus, ought to be considered and adjusted for in clinical decision support methods.

FRAX predicts cardiovascular risk in women undergoing osteoporosis screening: the Manitoba bone mineral density registry

Osteoporosis and cardiovascular disease (CVD) are highly prevalent in older women, with increasing evidence for shared risk factors and pathogenesis. Although FRAX was developed for the assessment of fracture risk, we hypothesized that it might also provide information on CVD risk. To test the ability of the FRAX tool and FRAX-defined risk factors to predict incident CVD in women undergoing osteoporosis screening with DXA, we performed a retrospective prognostic cohort study which included women aged 50 yr or older with a baseline DXA scan in the Manitoba Bone Mineral Density Registry between March 31, 1999 and March 31, 2018. FRAX scores for major osteoporotic fracture (MOF) were calculated on all participants. Incident MOF and major adverse CV events (MACE; hospitalized acute myocardial infarction [AMI], hospitalized non-hemorrhagic cerebrovascular disease [CVA], or all-cause death) were ascertained from linkage to population-based healthcare data. The study population comprised 59 696 women (mean age 65.7 ± 9.4 yr). Over mean 8.7 yr of observation, 6021 (10.1%) had MOF, 12 277 women (20.6%) had MACE, 2274 (3.8%) had AMI, 2061 (3.5%) had CVA, and 10 253 (17.2%) died. MACE rates per 1000 person-years by FRAX risk categories low (10-yr predicted MOF <10%), moderate (10%-19.9%) and high (≥20%) were 13.5, 34.0, and 64.6, respectively. Although weaker than the association with incident MOF, increasing FRAX quintile was associated with increasing risk for MACE (all P-trend <.001), even after excluding prior CVD and adjusting for age. HR for MACE per SD increase in FRAX was 1.99 (95%CI, 1.96-2.02). All FRAX-defined risk factors (except parental hip fracture and lower BMI) were independently associated with higher non-death CV events. Although FRAX is intended for fracture risk prediction, it has predictive value for cardiovascular risk.

Risk prediction models for cardiovascular events in hemodialysis patients: A systematic review

OBJECTIVE

To perform a systematic review of risk prediction models for cardiovascular (CV) events in hemodialysis (HD) patients, and provide a reference for the application and optimization of related prediction models.

METHODS

PubMed, The Cochrane Library, Web of Science, and Embase databases were searched from inception to 1 February 2023. Two authors independently conducted the literature search, selection, and screening. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was applied to evaluate the risk of bias and applicability of the included literature.

RESULTS

A total of nine studies containing 12 models were included, with performance measured by the area under the receiver operating characteristic curve (AUC) lying between 0.70 and 0.88. Age, diabetes mellitus (DM), C-reactive protein (CRP), and albumin (ALB) were the most commonly identified predictors of CV events in HD patients. While the included models demonstrated good applicability, there were still certain risks of bias, primarily related to inadequate handling of missing data and transformation of continuous variables, as well as a lack of model performance validation.

CONCLUSION

The included models showed good overall predictive performance and can assist healthcare professionals in the early identification of high-risk individuals for CV events in HD patients. In the future, the modeling methods should be improved, or the existing models should undergo external validation to provide better guidance for clinical practice.

A cost-effectiveness evaluation of a high-sensitivity troponin I guided voluntary cardiovascular risk assessment program for asymptomatic women in Croatia

Background

To estimate the effectiveness and cost-effectiveness of a high-sensitivity troponin I (hsTnI) guided cardiovascular risk assessment program in women in Croatia.

Methods

An observational study of a voluntary program for cardiovascular disease (CVD) risk assessment in women aged above 45 years with no specific symptoms, no confirmed or known coronary artery disease was conducted (WHP). Participants were stratified into three categories according to their hsTnI level. Subjects in the moderate or high-risk class were referred to cardiac work-up and invasive cardiovascular investigation as appropriate. Study information were applied to a discrete-event simulation model to estimate the cost-effectiveness of WHP against current practice. The number of CVD events and deaths, costs, and quality-adjusted life years (QALY) were assessed over 10 years from a societal perspective.

Results

Of 1034 women who participated in the program, 921 (89.1%), 100 (9.7%), and 13 (1.3%) subjects fall into the low, moderate, and high-risk class. Of 26 women referred for angiography, significant coronary artery disease (CAD) was diagnosed in 12 women (46.1%). WHP gained 15.8 (95%CI 12.8; 17.2) QALYs per 1000 subjects, increased costs by 490€ (95%CI 487; 500), decreased CVD-related mortality by 40%. At a willingness-to-pay threshold of 45,000 €/QALY, WHP was cost-effective with a probability of 90%. Model results were most sensitive to utility weights and cost of medical prevention.

Conclusions

Assessing the cardiovascular risk in asymptomatic women with hsTnI and guiding those at higher risk to further cardiac testing, identified individuals with CAD, could reduce CVD related burden, and would be cost-effective.

Predictive Utility of Irritability "In Context": Proof-of-Principle for an Early Childhood Mental Health Risk Calculator

OBJECTIVE

We provide proof-of-principle for a mental health risk calculator advancing clinical utility of the irritability construct for identification of young children at high risk for common, early onsetting syndromes.

METHOD

Data were harmonized from two longitudinal early childhood subsamples (total N = 403; 50.1% Male; 66.7% Nonwhite; Mage = 4.3 years). The independent subsamples were clinically enriched via disruptive behavior and violence (Subsample 1) and depression (Subsample 2). In longitudinal models, epidemiologic risk prediction methods for risk calculators were applied to test the utility of the transdiagnostic indicator, early childhood irritability, in the context of other developmental and social-ecological indicators to predict risk of internalizing/externalizing disorders at preadolescence (Mage = 9.9 years). Predictors were retained when they improved model discrimination (area under the receiver operating characteristic curve [AUC] and integrated discrimination index [IDI]) beyond the base demographic model.

RESULTS

Compared to the base model, the addition of early childhood irritability and adverse childhood experiences significantly improved the AUC (0.765) and IDI slope (0.192). Overall, 23% of preschoolers went on to develop a preadolescent internalizing/externalizing disorder. For preschoolers with both elevated irritability and adverse childhood experiences, the likelihood of an internalizing/externalizing disorder was 39-66%.

CONCLUSIONS

Predictive analytic tools enable personalized prediction of psychopathological risk for irritable young children, holding transformative potential for clinical translation.

Major Limitations of Cardiovascular Risk Scores

Background. Epidemiological studies conducted in extensive population cohorts have led to the creation of numerous cardiovascular risk predictor models. However, these tools have certain limitations that restrict its applicability. The aim behind the following work is to summarize today's best-known limitations of cardiovascular risk assessment models through presenting the critical analyses conducted in this area, with the intention of offering practitioners a comprehensive understanding of these restrictions. Critical analyses revealed that these scales exhibit numerous limitations that could impact their performance. Most of these models evaluate cardiovascular risk based on classic risk factors and other restrictions, thereby negatively affecting their sensitivity. Scientists have made significant advancements in improving cardiovascular risk models, tailoring them to accommodate a wide range of populations and devising scales for estimating cardiovascular risks that can account for all prevailing restrictions. Better understanding these limitations could improve the cardiovascular risk stratification.

Changes in muscle strength and risk of cardiovascular disease among middle-aged and older adults in China: Evidence from a prospective cohort study

BACKGROUND

Evidence indicates that low muscle strength is associated with an increased cardiovascular diseases (CVDs) risk. However, the association between muscle strength changes based on repeated measurements and CVD incidence remains unclear.

METHODS

The study used data from the China Health and Retirement Longitudinal Study in 2011 (Wave 1), 2013 (Wave 2), 2015 (Wave 3), and 2018 (Wave 4). Low muscle strength was defined as handgrip strength <28 kg for men or <18 kg for women, or chair-rising time ≥12 s. Based on changes in muscle strength from Waves 1 to 2, participants were categorized into four groups of Normal-Normal, Low-Normal, Normal-Low, and Low-Low. CVD events, including heart disease and stroke, were recorded using a self-reported questionnaire during Waves 3 and 4 visits. Cox proportional hazards models were used to investigate the association between muscle strength changes and CVD incidence after multivariable adjustments. Hazard ratios (HRs) and 95% confidence intervals (95% CIs) were estimated with the Normal-Normal group as the reference.

RESULTS

A total of 1164 CVD cases were identified among 6608 participants. Compared to participants with sustained normal muscle strength, the CVD risks increased progressively across groups of the Low-Normal (HR = 1.20, 95% CI: 1.01-1.43), the Normal-Low (HR = 1.35, 95% CI: 1.14-1.60), and the Low-Low (HR = 1.76, 95% CI: 1.49-2.07). Similar patterns were observed for the significant associations between muscle strength status and the incidence risks of heart disease and stroke. Subgroup analyses showed that the significant associations between CVD and muscle strength changes were consistent across age, sex, and body mass index (BMI) categories.

CONCLUSIONS

The study found that muscle strength changes were associated with CVD risk. This suggests that continuous tracking of muscle status may be helpful in screening cardiovascular risk.

Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review

BACKGROUND

A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation.

METHODS

PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789).

RESULTS

In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively.

CONCLUSION

AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

The validity of electronic health data for measuring smoking status: a systematic review and meta-analysis

BACKGROUND

Smoking is a risk factor for many chronic diseases. Multiple smoking status ascertainment algorithms have been developed for population-based electronic health databases such as administrative databases and electronic medical records (EMRs). Evidence syntheses of algorithm validation studies have often focused on chronic diseases rather than risk factors. We conducted a systematic review and meta-analysis of smoking status ascertainment algorithms to describe the characteristics and validity of these algorithms.

METHODS

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were followed. We searched articles published from 1990 to 2022 in EMBASE, MEDLINE, Scopus, and Web of Science with key terms such as validity, administrative data, electronic health records, smoking, and tobacco use. The extracted information, including article characteristics, algorithm characteristics, and validity measures, was descriptively analyzed. Sources of heterogeneity in validity measures were estimated using a meta-regression model. Risk of bias (ROB) in the reviewed articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool.

RESULTS

The initial search yielded 2086 articles; 57 were selected for review and 116 algorithms were identified. Almost three-quarters (71.6%) of algorithms were based on EMR data. The algorithms were primarily constructed using diagnosis codes for smoking-related conditions, although prescription medication codes for smoking treatments were also adopted. About half of the algorithms were developed using machine-learning models. The pooled estimates of positive predictive value, sensitivity, and specificity were 0.843, 0.672, and 0.918 respectively. Algorithm sensitivity and specificity were highly variable and ranged from 3 to 100% and 36 to 100%, respectively. Model-based algorithms had significantly greater sensitivity (p = 0.006) than rule-based algorithms. Algorithms for EMR data had higher sensitivity than algorithms for administrative data (p = 0.001). The ROB was low in most of the articles (76.3%) that underwent the assessment.

CONCLUSIONS

Multiple algorithms using different data sources and methods have been proposed to ascertain smoking status in electronic health data. Many algorithms had low sensitivity and positive predictive value, but the data source influenced their validity. Algorithms based on machine-learning models for multiple linked data sources have improved validity.

The Semmelweis Study: a longitudinal occupational cohort study within the framework of the Semmelweis Caring University Model Program for supporting healthy aging

The Semmelweis Study is a prospective occupational cohort study that seeks to enroll all employees of Semmelweis University (Budapest, Hungary) aged 25 years and older, with a population of 8866 people, 70.5% of whom are women. The study builds on the successful experiences of the Whitehall II study and aims to investigate the complex relationships between lifestyle, environmental, and occupational risk factors, and the development and progression of chronic age-associated diseases. An important goal of the Semmelweis Study is to identify groups of people who are aging unsuccessfully and therefore have an increased risk of developing age-associated diseases. To achieve this, the study takes a multidisciplinary approach, collecting economic, social, psychological, cognitive, health, and biological data. The Semmelweis Study comprises a baseline data collection with open healthcare data linkage, followed by repeated data collection waves every 5 years. Data are collected through computer-assisted self-completed questionnaires, followed by a physical health examination, physiological measurements, and the assessment of biomarkers. This article provides a comprehensive overview of the Semmelweis Study, including its origin, context, objectives, design, relevance, and expected contributions.

Epigenetic Contributions to Clinical Risk Prediction of Cardiovascular Disease

BACKGROUND

Cardiovascular disease (CVD) is among the leading causes of death worldwide. The discovery of new omics biomarkers could help to improve risk stratification algorithms and expand our understanding of molecular pathways contributing to the disease. Here, ASSIGN-a cardiovascular risk prediction tool recommended for use in Scotland-was examined in tandem with epigenetic and proteomic features in risk prediction models in ≥12 657 participants from the Generation Scotland cohort.

METHODS

Previously generated DNA methylation-derived epigenetic scores (EpiScores) for 109 protein levels were considered, in addition to both measured levels and an EpiScore for cTnI (cardiac troponin I). The associations between individual protein EpiScores and the CVD risk were examined using Cox regression (ncases≥1274; ncontrols≥11 383) and visualized in a tailored R application. Splitting the cohort into independent training (n=6880) and test (n=3659) subsets, a composite CVD EpiScore was then developed.

RESULTS

Sixty-five protein EpiScores were associated with incident CVD independently of ASSIGN and the measured concentration of cTnI (P<0.05), over a follow-up of up to 16 years of electronic health record linkage. The most significant EpiScores were for proteins involved in metabolic, immune response, and tissue development/regeneration pathways. A composite CVD EpiScore (based on 45 protein EpiScores) was a significant predictor of CVD risk independent of ASSIGN and the concentration of cTnI (hazard ratio, 1.32; P=3.7×10-3; 0.3% increase in C-statistic).

CONCLUSIONS

EpiScores for circulating protein levels are associated with CVD risk independent of traditional risk factors and may increase our understanding of the etiology of the disease.

The implications of competing risks and direct treatment disutility in cardiovascular disease and osteoporotic fracture: risk prediction and cost effectiveness analysis

Background

Clinical guidelines commonly recommend preventative treatments for people above a risk threshold. Therefore, decision-makers must have faith in risk prediction tools and model-based cost-effectiveness analyses for people at different levels of risk. Two problems that arise are inadequate handling of competing risks of death and failing to account for direct treatment disutility (i.e. the hassle of taking treatments). We explored these issues using two case studies: primary prevention of cardiovascular disease using statins and osteoporotic fracture using bisphosphonates.

Objectives

Externally validate three risk prediction tools [QRISK®3, QRISK®-Lifetime, QFracture-2012 (ClinRisk Ltd, Leeds, UK)]; derive and internally validate new risk prediction tools for cardiovascular disease [competing mortality risk model with Charlson Comorbidity Index (CRISK-CCI)] and fracture (CFracture), accounting for competing-cause death; quantify direct treatment disutility for statins and bisphosphonates; and examine the effect of competing risks and direct treatment disutility on the cost-effectiveness of preventative treatments.

Design, participants, main outcome measures, data sources

Discrimination and calibration of risk prediction models (Clinical Practice Research Datalink participants: aged 25-84 years for cardiovascular disease and aged 30-99 years for fractures); direct treatment disutility was elicited in online stated-preference surveys (people with/people without experience of statins/bisphosphonates); costs and quality-adjusted life-years were determined from decision-analytic modelling (updated models used in National Institute for Health and Care Excellence decision-making).

Results

CRISK-CCI has excellent discrimination, similar to that of QRISK3 (Harrell's c = 0.864 vs. 0.865, respectively, for women; and 0.819 vs. 0.834, respectively, for men). CRISK-CCI has systematically better calibration, although both models overpredict in high-risk subgroups. People recommended for treatment (10-year risk of ≥ 10%) are younger when using QRISK-Lifetime than when using QRISK3, and have fewer observed events in a 10-year follow-up (4.0% vs. 11.9%, respectively, for women; and 4.3% vs. 10.8%, respectively, for men). QFracture-2012 underpredicts fractures, owing to under-ascertainment of events in its derivation. However, there is major overprediction among people aged 85-99 years and/or with multiple long-term conditions. CFracture is better calibrated, although it also overpredicts among older people. In a time trade-off exercise (n = 879), statins exhibited direct treatment disutility of 0.034; for bisphosphonates, it was greater, at 0.067. Inconvenience also influenced preferences in best-worst scaling (n = 631). Updated cost-effectiveness analysis generates more quality-adjusted life-years among people with below-average cardiovascular risk and fewer among people with above-average risk. If people experience disutility when taking statins, the cardiovascular risk threshold at which benefits outweigh harms rises with age (≥ 8% 10-year risk at 40 years of age; ≥ 38% 10-year risk at 80 years of age). Assuming that everyone experiences population-average direct treatment disutility with oral bisphosphonates, treatment is net harmful at all levels of risk.

Limitations

Treating data as missing at random is a strong assumption in risk prediction model derivation. Disentangling the effect of statins from secular trends in cardiovascular disease in the previous two decades is challenging. Validating lifetime risk prediction is impossible without using very historical data. Respondents to our stated-preference survey may not be representative of the population. There is no consensus on which direct treatment disutilities should be used for cost-effectiveness analyses. Not all the inputs to the cost-effectiveness models could be updated.

Conclusions

Ignoring competing mortality in risk prediction overestimates the risk of cardiovascular events and fracture, especially among older people and those with multimorbidity. Adjustment for competing risk does not meaningfully alter cost-effectiveness of these preventative interventions, but direct treatment disutility is measurable and has the potential to alter the balance of benefits and harms. We argue that this is best addressed in individual-level shared decision-making.

Study registration

This study is registered as PROSPERO CRD42021249959.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme (NIHR award ref: 15/12/22) and is published in full in Health and Social Care Delivery Research; Vol. 12, No. 4. See the NIHR Funding and Awards website for further award information.

Precision prognostics for cardiovascular disease in Type 2 diabetes: a systematic review and meta-analysis

BACKGROUND

Precision medicine has the potential to improve cardiovascular disease (CVD) risk prediction in individuals with Type 2 diabetes (T2D).

METHODS

We conducted a systematic review and meta-analysis of longitudinal studies to identify potentially novel prognostic factors that may improve CVD risk prediction in T2D. Out of 9380 studies identified, 416 studies met inclusion criteria. Outcomes were reported for 321 biomarker studies, 48 genetic marker studies, and 47 risk score/model studies.

RESULTS

Out of all evaluated biomarkers, only 13 showed improvement in prediction performance. Results of pooled meta-analyses, non-pooled analyses, and assessments of improvement in prediction performance and risk of bias, yielded the highest predictive utility for N-terminal pro b-type natriuretic peptide (NT-proBNP) (high-evidence), troponin-T (TnT) (moderate-evidence), triglyceride-glucose (TyG) index (moderate-evidence), Genetic Risk Score for Coronary Heart Disease (GRS-CHD) (moderate-evidence); moderate predictive utility for coronary computed tomography angiography (low-evidence), single-photon emission computed tomography (low-evidence), pulse wave velocity (moderate-evidence); and low predictive utility for C-reactive protein (moderate-evidence), coronary artery calcium score (low-evidence), galectin-3 (low-evidence), troponin-I (low-evidence), carotid plaque (low-evidence), and growth differentiation factor-15 (low-evidence). Risk scores showed modest discrimination, with lower performance in populations different from the original development cohort.

CONCLUSIONS

Despite high interest in this topic, very few studies conducted rigorous analyses to demonstrate incremental predictive utility beyond established CVD risk factors for T2D. The most promising markers identified were NT-proBNP, TnT, TyG and GRS-CHD, with the highest strength of evidence for NT-proBNP. Further research is needed to determine their clinical utility in risk stratification and management of CVD in T2D.

History of Infertility and Midlife Cardiovascular Health in Female Individuals

Importance

Fertility status is a marker for future health, and infertility has been associated with risk for later cancer and diabetes, but associations with midlife cardiovascular health (CVH) in female individuals remain understudied.

Objective

To evaluate the association of infertility history with CVH at midlife (approximately age 50 years) among parous individuals.

Design, Setting, and Participants

Project Viva is a prospective cohort study of pregnant participants enrolled between 1999 and 2002 who delivered a singleton live birth in the greater Boston, Massachusetts, area. Infertility history was collected at a midlife visit between 2017 and 2021, approximately 18 years after enrollment. Data analysis was performed from January to June 2023.

Exposures

The primary exposure was any lifetime history of infertility identified by self-report, medical record, diagnosis, or claims for infertility treatment.

Main Outcomes and Measures

The American Heart Association's Life's Essential 8 (LE8) is a construct for ranking CVH that includes scores from 0 to 100 (higher scores denote better health status) in 4 behavioral (diet, physical activity, sleep, and smoking status) and 4 biomedical (body mass index, blood pressure, blood lipids, and glycemia) domains to form an overall assessment of CVH. Associations of a history of infertility (yes or no) with mean LE8 total, behavioral, biomedical, and blood biomarker (lipids and glycemia) scores were examined, adjusting for age at outcome (midlife visit), race and ethnicity, education, household income, age at menarche, and perceived body size at age 10 years.

Results

Of 468 included participants (mean [SD] age at the midlife visit, 50.6 [5.3] years) with exposure and outcome data, 160 (34.2%) experienced any infertility. Mean (SD) LE8 scores were 76.3 (12.2) overall, 76.5 (13.4) for the behavioral domain, 76.0 (17.5) for the biomedical domain, and 78.9 (19.2) for the blood biomarkers subdomain. In adjusted models, the estimated overall LE8 score at midlife was 2.94 points lower (95% CI, -5.13 to -0.74 points), the biomedical score was 4.07 points lower (95% CI, -7.33 to -0.78 points), and the blood subdomain score was 5.98 points lower (95% CI, -9.71 to -2.26 points) among those with vs without history of infertility. The point estimate also was lower for the behavioral domain score (β = -1.81; 95% CI, -4.28 to 0.66), although the result was not statistically significant.

Conclusions and Relevance

This cohort study of parous individuals found evidence for an association between a history of infertility and lower overall and biomedical CVH scores. Future study of enhanced cardiovascular preventive strategies among those who experience infertility is warranted.

Modelling the effects of the exposome score within the extended psychosis phenotype

It has been reported that cumulative measures of risk factors for psychosis might help to predict its development. However, it remains unknown as to whether these measures are also associated with the extended psychosis phenotype that refers to a continuum of features bridging subclinical symptoms with clinically relevant outcomes. In this study, we aimed to investigate the association of the exposome score (ES) with psychosis risk in a non-clinical population. A total of 1100 non-clinical adults (aged 18-35 years, 51.4% females) with a negative history of psychiatric treatment were recruited. The Prodromal Questionnaire-16 (PQ-16) was used to screen for psychosis risk. Self-reports were used to record environmental exposures. The ES was significantly higher in participants with the positive PQ-16 screening. Specifically, the prevalence of obstetric complications, non-right handedness, all categories of childhood trauma, and problematic cannabis use was significantly higher in this group of participants. A network analysis demonstrated that the ES was directly connected not only to items representing psychotic experiences ("paranoid thoughts", "a lack of control over own ideas or thoughts", "thought echo", and "being distracted by distant sounds") but also those covering depressive or anxiety symptoms ("uninterested in things used to enjoy" and "feeling anxious when meeting people for the first time"). In conclusion, the ES is associated with the extended psychosis phenotype, suggesting its potential to identify individuals who may benefit from further psychosis risk assessment. The ES appears to contribute to non-specific psychopathology, which may, in some cases, progress to psychosis.

Pitfalls and potentials in simulation studies: Questionable research practices in comparative simulation studies allow for spurious claims of superiority of any method

Comparative simulation studies are workhorse tools for benchmarking statistical methods. As with other empirical studies, the success of simulation studies hinges on the quality of their design, execution, and reporting. If not conducted carefully and transparently, their conclusions may be misleading. In this paper, we discuss various questionable research practices, which may impact the validity of simulation studies, some of which cannot be detected or prevented by the current publication process in statistics journals. To illustrate our point, we invent a novel prediction method with no expected performance gain and benchmark it in a preregistered comparative simulation study. We show how easy it is to make the method appear superior over well-established competitor methods if questionable research practices are employed. Finally, we provide concrete suggestions for researchers, reviewers, and other academic stakeholders for improving the methodological quality of comparative simulation studies, such as preregistering simulation protocols, incentivizing neutral simulation studies, and code and data sharing.

Using Repeated Measurements to Predict Cardiovascular Risk in Patients With Type 2 Diabetes Mellitus

The QRISK cardiovascular disease (CVD) risk assessment model is not currently optimized for patients with type 2 diabetes mellitus (T2DM). We aim to identify if the abundantly available repeatedly measured data for patients with T2D improves the predictive capability of QRISK to support the decision-making process regarding CVD prevention in patients with T2DM. We identified patients with T2DM aged 25 to 85, not on statin treatment and without pre-existing CVD from the IQVIA Medical Research Data United Kingdom primary care database and then followed them up until the first diagnosis of CVD, ischemic heart disease, or stroke/transient ischemic attack. We included traditional, nontraditional risk factors and relevant treatments for our analysis. We then undertook a Cox's hazards model accounting for time-dependent covariates to estimate the hazard rates for each risk factor and calculated a 10-year risk score. Models were developed for males and females separately. We tested the performance of our models using validation data and calculated discrimination and calibration statistics. The study included 198,835 (180,143 male with 11,976 outcomes and 90,466 female with 8,258 outcomes) patients. The 10-year predicted survival probabilities for females was 0.87 (0.87 to 0.87), whereas the observed survival estimates from the Kaplan-Meier curve for all female models was 0.87 (0.86 to 0.87). The predicted and observed survival estimates for males were 0.84 (0.84 to 0.84) and 0.84 (0.83 to 0.84) respectively. The Harrell's C-index of all female models and all male models were 0.71 and 0.69 respectively. We found that including time-varying repeated measures, only mildly improved CVD risk prediction for T2DM patients in comparison to the current practice standard. We advocate for further research using time-varying data to identify if the involvement of further covariates may improve the accuracy of currently accepted prediction models.

Predictive value of clinical features and CT radiomics in the efficacy of hip preservation surgery with fibula allograft

BACKGROUND

Despite being an effective treatment for osteonecrosis of the femoral head (ONFH), hip preservation surgery with fibula allograft (HPS&FA) still experiences numerous failures. Developing a prediction model based on clinical and radiomics predictors holds promise for addressing this issue.

METHODS

This study included 112 ONFH patients who underwent HPS&FA and were randomly divided into training and validation cohorts. Clinical data were collected, and clinically significant predictors were identified using univariate and multivariate analyses to develop a clinical prediction model (CPM). Simultaneously, the least absolute shrinkage and selection operator method was employed to select optimal radiomics features from preoperative hip computed tomography images, forming a radiomics prediction model (RPM). Furthermore, to enhance prediction accuracy, a clinical-radiomics prediction model (CRPM) was constructed by integrating all predictors. The predictive performance of the models was evaluated using receiver operating characteristic curve (ROC), area under the curve (AUC), DeLong test, calibration curve, and decision curve analysis.

RESULTS

Age, Japanese Investigation Committee classification, postoperative use of glucocorticoids or alcohol, and non-weightbearing time were identified as clinical predictors. The AUC of the ROC curve for the CPM was 0.847 in the training cohort and 0.762 in the validation cohort. After incorporating radiomics features, the CRPM showed improved AUC values of 0.875 in the training cohort and 0.918 in the validation cohort. Decision curves demonstrated that the CRPM yielded greater medical benefit across most risk thresholds.

CONCLUSION

The CRPM serves as an efficient prediction model for assessing HPS&FA efficacy and holds potential as a personalized perioperative intervention tool to enhance HPS&FA success rates.

Five critical quality criteria for artificial intelligence-based prediction models

To raise the quality of clinical artificial intelligence (AI) prediction modelling studies in the cardiovascular health domain and thereby improve their impact and relevancy, the editors for digital health, innovation, and quality standards of the European Heart Journal propose five minimal quality criteria for AI-based prediction model development and validation studies: complete reporting, carefully defined intended use of the model, rigorous validation, large enough sample size, and openness of code and software.

A deep learning system for retinal vessel calibre improves cardiovascular risk prediction in Asians with chronic kidney disease

Backgraund

Cardiovascular disease (CVD) and mortality is elevated in chronic kidney disease (CKD). Retinal vessel calibre in retinal photographs is associated with cardiovascular risk and automated measurements may aid CVD risk prediction.

Methods

Retrospective cohort study of 860 Chinese, Malay and Indian participants aged 40-80 years with CKD [estimated glomerular filtration rate (eGFR) <60 ml/min/1.73 m2] who attended the baseline visit (2004-2011) of the Singapore Epidemiology of Eye Diseases Study. Retinal vessel calibre measurements were obtained by a deep learning system (DLS). Incident CVD [non-fatal acute myocardial infarction (MI) and stroke, and death due to MI, stroke and other CVD] in those who were free of CVD at baseline was ascertained until 31 December 2019. Risk factors (established, kidney, and retinal features) were examined using Cox proportional hazards regression models. Model performance was assessed for discrimination, fit, and net reclassification improvement (NRI).

Results

Incident CVD occurred in 289 (33.6%) over mean follow-up of 9.3 (4.3) years. After adjusting for established cardiovascular risk factors, eGFR [adjusted HR 0.98 (95% CI: 0.97-0.99)] and retinal arteriolar narrowing [adjusted HR 1.40 (95% CI: 1.17-1.68)], but not venular dilation, were independent predictors for CVD in CKD. The addition of eGFR and retinal features to established cardiovascular risk factors improved model discrimination with significantly better fit and better risk prediction according to the low (<15%), intermediate (15-29.9%), and high (30% or more) risk categories (NRI 5.8%), and with higher risk thresholds (NRI 12.7%).

Conclusions

Retinal vessel calibre measurements by DLS were significantly associated with incident CVD independent of established CVD risk factors. Addition of kidney function and retinal vessel calibre parameters may improve CVD risk prediction among Asians with CKD.

Validity of the models predicting 10-year risk of cardiovascular diseases in Asia: A systematic review and prediction model meta-analysis

We aimed to review the validity of existing prediction models for cardiovascular diseases (CVDs) in Asia. In this systematic review and meta-analysis, we included studies that validated prediction models for CVD risk in the general population in Asia. Various databases, including PubMed, Web of Science conference proceedings citation index, Scopus, Global Index Medicus of the World Health Organization (WHO), and Open Access Thesis and Dissertations (OATD), were searched up to November 2022. Additional studies were identified through reference lists and related reviews. The risk of bias was assessed using the PROBAST prediction model risk of bias assessment tool. Meta-analyses were performed using the random effects model, focusing on the C-statistic as a discrimination index and the observed-to-expected ratio (OE) as a calibration index. Out of 1315 initial records, 16 studies were included, with 21 external validations of six models in Asia. The validated models consisted of Framingham models, pooled cohort equations (PCEs), SCORE, Globorisk, and WHO models, combined with the results of the first four models. The pooled C-statistic for men ranged from 0.72 (95% CI 0.70 to 0.75; PCEs) to 0.76 (95% CI 0.74 to 0.78; Framingham general CVD). In women, it varied from 0.74 (95% CI 0.22 to 0.97; SCORE) to 0.79 (95% CI 0.74 to 0.83; Framingham general CVD). The pooled OE ratio for men ranged from 0.21 (95% CI 0.018 to 2.49; Framingham CHD) to 1.11 (95%CI 0.65 to 1.89; PCEs). In women, it varied from 0.28 (95%CI 0.33 to 2.33; Framingham CHD) to 1.81 (95% CI 0.90 to 3.64; PCEs). The Framingham, PCEs, and SCORE models exhibited acceptable discrimination but poor calibration in predicting the 10-year risk of CVDs in Asia. Recalibration and updates are necessary before implementing these models in the region.

Prediction of fetal and neonatal outcomes after preterm manifestations of placental insufficiency: systematic review of prediction models

OBJECTIVES

To identify all prediction models for fetal and neonatal outcomes in pregnancies with preterm manifestations of placental insufficiency (gestational hypertension, pre-eclampsia, HELLP syndrome or fetal growth restriction with its onset before 37 weeks' gestation) and to assess the quality of the models and their performance on external validation.

METHODS

A systematic literature search was performed in PubMed, Web of Science and EMBASE. Studies describing prediction models for fetal/neonatal mortality or significant neonatal morbidity in patients with preterm placental insufficiency disorders were included. Data extraction was performed using the CHARMS checklist. Risk of bias was assessed using PROBAST. Literature selection and data extraction were performed by two researchers independently.

RESULTS

Our literature search yielded 22 491 unique publications. Fourteen were included after full-text screening of 218 articles that remained after initial exclusions. The studies derived a total of 41 prediction models, including four models in the setting of pre-eclampsia or HELLP, two models in the setting of fetal growth restriction and/or pre-eclampsia and 35 models in the setting of fetal growth restriction. None of the models was validated externally, and internal validation was performed in only two studies. The final models contained mainly ultrasound (Doppler) markers as predictors of fetal/neonatal mortality and neonatal morbidity. Discriminative properties were reported for 27/41 models (c-statistic between 0.6 and 0.9). Only two studies presented a calibration plot. The risk of bias was assessed as unclear in one model and high for all other models, mainly owing to the use of inappropriate statistical methods.

CONCLUSIONS

We identified 41 prediction models for fetal and neonatal outcomes in pregnancies with preterm manifestations of placental insufficiency. All models were considered to be of low methodological quality, apart from one that had unclear methodological quality. Higher-quality models and external validation studies are needed to inform clinical decision-making based on prediction models. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

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.

Prioritising cardiovascular disease risk assessment to high risk individuals based on primary care records

OBJECTIVE

To provide quantitative evidence for systematically prioritising individuals for full formal cardiovascular disease (CVD) risk assessment using primary care records with a novel tool (eHEART) with age- and sex- specific risk thresholds.

METHODS AND ANALYSIS

eHEART was derived using landmark Cox models for incident CVD with repeated measures of conventional CVD risk predictors in 1,642,498 individuals from the Clinical Practice Research Datalink. Using 119,137 individuals from UK Biobank, we modelled the implications of initiating guideline-recommended statin therapy using eHEART with age- and sex-specific prioritisation thresholds corresponding to 5% false negative rates to prioritise adults aged 40-69 years in a population in England for invitation to a formal CVD risk assessment.

RESULTS

Formal CVD risk assessment on all adults would identify 76% and 49% of future CVD events amongst men and women respectively, and 93 (95% CI: 90, 95) men and 279 (95% CI: 259, 297) women would need to be screened (NNS) to prevent one CVD event. In contrast, if eHEART was first used to prioritise individuals for formal CVD risk assessment, we would identify 73% and 47% of future events amongst men and women respectively, and a NNS of 75 (95% CI: 72, 77) men and 162 (95% CI: 150, 172) women. Replacing the age- and sex-specific prioritisation thresholds with a 10% threshold identify around 10% less events.

CONCLUSIONS

The use of prioritisation tools with age- and sex-specific thresholds could lead to more efficient CVD assessment programmes with only small reductions in effectiveness at preventing new CVD events.

Machine learning models for predicting the risk factor of carotid plaque in cardiovascular disease

Introduction

Cardiovascular disease (CVD) is a group of diseases involving the heart or blood vessels and represents a leading cause of death and disability worldwide. Carotid plaque is an important risk factor for CVD that can reflect the severity of atherosclerosis. Accordingly, developing a prediction model for carotid plaque formation is essential to assist in the early prevention and management of CVD.

Methods

In this study, eight machine learning algorithms were established, and their performance in predicting carotid plaque risk was compared. Physical examination data were collected from 4,659 patients and used for model training and validation. The eight predictive models based on machine learning algorithms were optimized using the above dataset and 10-fold cross-validation. The Shapley Additive Explanations (SHAP) tool was used to compute and visualize feature importance. Then, the performance of the models was evaluated according to the area under the receiver operating characteristic curve (AUC), feature importance, accuracy and specificity.

Results

The experimental results indicated that the XGBoost algorithm outperformed the other machine learning algorithms, with an AUC, accuracy and specificity of 0.808, 0.749 and 0.762, respectively. Moreover, age, smoke, alcohol drink and BMI were the top four predictors of carotid plaque formation. It is feasible to predict carotid plaque risk using machine learning algorithms.

Conclusions

This study indicates that our models can be applied to routine chronic disease management procedures to enable more preemptive, broad-based screening for carotid plaque and improve the prognosis of CVD patients.

Study protocol for development and validation of a single tool to assess risks of stroke, diabetes mellitus, myocardial infarction and dementia: DemNCD-Risk

INTRODUCTION

Current efforts to reduce dementia focus on prevention and risk reduction by targeting modifiable risk factors. As dementia and cardiometabolic non-communicable diseases (NCDs) share risk factors, a single risk-estimating tool for dementia and multiple NCDs could be cost-effective and facilitate concurrent assessments as compared with a conventional single approach. The aim of this study is to develop and validate a new risk tool that estimates an individual's risk of developing dementia and other NCDs including diabetes mellitus, stroke and myocardial infarction. Once validated, it could be used by the public and general practitioners.

METHODS AND ANALYSIS

Ten high-quality cohort studies from multiple countries were identified, which met eligibility criteria, including large representative samples, long-term follow-up, data on clinical diagnoses of dementia and NCDs, recognised modifiable risk factors for the four NCDs and mortality data. Pooled harmonised data from the cohorts will be used, with 65% randomly allocated for development of the predictive model and 35% for testing. Predictors include sociodemographic characteristics, general health risk factors and lifestyle/behavioural risk factors. A subdistribution hazard model will assess the risk factors' contribution to the outcome, adjusting for competing mortality risks. Point-based scoring algorithms will be built using predictor weights, internally validated and the discriminative ability and calibration of the model will be assessed for the outcomes. Sensitivity analyses will include recalculating risk scores using logistic regression.

ETHICS AND DISSEMINATION

Ethics approval is provided by the University of New South Wales Human Research Ethics Committee (UNSW HREC; protocol numbers HC200515, HC3413). All data are deidentified and securely stored on servers at Neuroscience Research Australia. Study findings will be presented at conferences and published in peer-reviewed journals. The tool will be accessible as a public health resource. Knowledge translation and implementation work will explore strategies to apply the tool in clinical practice.

Blood-Based and Imaging Biomarkers of Atherosclerosis

Atherosclerosis is the main cause of arterial thrombosis, causing acute occlusive cardiovascular syndromes. Numerous risk prediction models have been developed, which mathematically combine multiple predictors, to estimate the risk of developing cardiovascular events. Current risk models typically do not include information from biomarkers that can potentially improve these existing prediction models especially if they are pathophysiologically relevant. Numerous cardiovascular disease biomarkers have been investigated that have focused on known pathophysiological pathways including those related to cardiac stress, inflammation, matrix remodelling, and endothelial dysfunction. Imaging biomarkers have also been studied that have yielded promising results with a potential higher degree of clinical applicability in detection of atherosclerosis and cardiovascular event prediction. To further improve therapy decision-making and guidance, there is continuing intense research on emerging biologically relevant biomarkers. As the pathogenesis of cardiovascular disease is multifactorial, improvements in discrimination and reclassification in risk prediction models will likely involve multiple biomarkers. This article will provide an overview of the literature on potential blood-based and imaging biomarkers of atherosclerosis studied so far, as well as potential future directions.

Feasibility and Clinical Utility of Prediction Models for Breast Cancer-Related Lymphedema Incorporating Racial Differences in Disease Incidence

Importance

Breast cancer-related lymphedema (BCRL) is a common complication of axillary lymph node dissection (ALND) but can also develop after sentinel lymph node biopsy (SLNB). Several models have been developed to predict the risk of disease development before and after surgery; however, these models have shortcomings that include the omission of race, inclusion of variables that are not readily available to patients, low sensitivity or specificity, and lack of risk assessment for patients treated with SLNB.

Objective

To create simple and accurate prediction models for BCRL that can be used to estimate preoperative or postoperative risk.

Design, Setting, and Participants

In this prognostic study, women with breast cancer who underwent ALND or SLNB from 1999 to 2020 at Memorial Sloan Kettering Cancer Center and the Mayo Clinic were included. Data were analyzed from September to December 2022.

Main Outcomes and Measures

Diagnosis of lymphedema based on measurements. Two predictive models were formulated via logistic regression: a preoperative model (model 1) and a postoperative model (model 2). Model 1 was externally validated using a cohort of 34 438 patients with an International Classification of Diseases diagnosis of breast cancer.

Results

Of 1882 included patients, all were female, and the mean (SD) age was 55.6 (12.2) years; 80 patients (4.3%) were Asian, 190 (10.1%) were Black, 1558 (82.8%) were White, and 54 (2.9%) were another race (including American Indian and Alaska Native, other race, patient refused to disclose, or unknown). A total of 218 patients (11.6%) were diagnosed with BCRL at a mean (SD) follow-up of 3.9 (1.8) years. The BCRL rate was significantly higher among Black women (42 of 190 [22.1%]) compared with all other races (Asian, 10 of 80 [12.5%]; White, 158 of 1558 [10.1%]; other race, 8 of 54 [14.8%]; P < .001). Model 1 included age, weight, height, race, ALND/SLNB status, any radiation therapy, and any chemotherapy. Model 2 included age, weight, race, ALND/SLNB status, any chemotherapy, and patient-reported arm swelling. Accuracy was 73.0% for model 1 (sensitivity, 76.6%; specificity, 72.5%; area under the receiver operating characteristic curve [AUC], 0.78; 95% CI, 0.75-0.81) at a cutoff of 0.18, and accuracy was 81.1% for model 2 (sensitivity, 78.0%; specificity, 81.5%; AUC, 0.86; 95% CI, 0.83-0.88) at a cutoff of 0.10. Both models demonstrated high AUCs on external (model 1: 0.75; 95% CI, 0.74-0.76) or internal (model 2: 0.82; 95% CI, 0.79-0.85) validation.

Conclusions and Relevance

In this study, preoperative and postoperative prediction models for BCRL were highly accurate and clinically relevant tools comprised of accessible inputs and underscored the effects of racial differences on BCRL risk. The preoperative model identified high-risk patients who require close monitoring or preventative measures. The postoperative model can be used for screening of high-risk patients, thus decreasing the need for frequent clinic visits and arm volume measurements.

Genetics-based risk scores for prediction of premature coronary artery disease

Premature coronary artery disease (CAD) is endemic in India. Global Burden of Diseases study has reported that it led to 286,000 deaths in 2019 in India. Many of these patients have standard risk factors but a third have none. Clinical risk algorithms and imaging provide limited risk information in premature CAD. CAD is multifactorial and studies have now focused on the predictive capability of clusters of genes and single nucleotide polymorphisms (SNPs) using gene risk score (GRS). Older studies combined data from 10 to 12 genes and 100-500 SNPs to calculate GRS, however, following the advent of genome-wide association studies (GWAS), millions of SNPs have been incorporated. Studies have reported that GWAS-based GRS may be more discriminative than conventional tools. Recent studies, especially among South Asians, have reported that GRS improves net reclassification by 15% (12-19%) for younger individuals. Aggressive lifestyle interventions and lipid-lowering therapies can ameliorate risk in high-GRS individuals and potentially prevent premature CAD.

A comparative assessment between Globorisk and WHO cardiovascular disease risk scores: a population-based study

The Globorisk and WHO cardiovascular risk prediction models are country-specific and region-specific, respectively. The goal of this study was to assess the agreement and correlation between the WHO and Globorisk 10-year cardiovascular disease risk prediction models. The baseline data of 6796 individuals aged 40-74 years who participated in the Fasa cohort study without a history of cardiovascular disease or stroke at baseline were included. In the WHO and Globorisk models scores were calculated using age, sex, systolic blood pressure (SBP), current smoking, diabetes, and total cholesterol for laboratory-based risk and age, sex, SBP, current smoking, and body mass index (BMI) for non-laboratory-based risk (office-based or BMI-based). In Globorisk and WHO risk agreement across risk categories (low, moderate, and high) was examined using the kappa statistic. Also, Pearson correlation coefficients and scatter plots were used to assess the correlation between Globorisk and WHO models. Bland-Altman plots were presented for determination agreement between Globorisk and WHO risk scores in individual's level. In laboratory-based models, agreement across categories was substantial in the overall population (kappa values: 0.75) and also for females (kappa values: 0.74) and males (kappa values: 0.76), when evaluated separately. In non-laboratory-based models, agreement across categories was substantial for the whole population (kappa values: 0.78), and almost perfect for among males (kappa values: 0.82) and substantial for females (kappa values: 0.73). The results showed a very strong positive correlation (r ≥ 0.95) between WHO and Globorisk laboratory-based scores for the whole population, males, and females and also a very strong positive correlation (r > 0.95) between WHO and Globorisk non-laboratory-based scores for the whole population, males, and females. In the laboratory-based models, the limit of agreements was better in males (95%CI 2.1 to - 4.2%) than females (95%CI 4.3 to - 7.3%). Also, in the non-laboratory-based models, the limit of agreements was better in males (95%CI 2.9 to - 4.0%) than females (95%CI 3.2 to - 6.1%). There was a good agreement between both the laboratory-based and the non-laboratory-based WHO models and the Globorisk models. The correlation between two models was very strongly positive. However, in the Globorisk models, more people were in high-risk group than in the WHO models. The scatter plots and Bland-Altman plots showed systematic differences between the two scores that vary according to the level of risk. So, for these models may be necessary to modify the cut points of risk groups. The validity of these models must be determined for this population.

Can spirometry improve the performance of cardiovascular risk model in high-risk Eastern European countries?

Aims

Impaired lung function has been strongly associated with cardiovascular disease (CVD) events. We aimed to assess the additive prognostic value of spirometry indices to the risk estimation of CVD events in Eastern European populations in this study.

Methods

We randomly selected 14,061 individuals with a mean age of 59 ± 7.3 years without a previous history of cardiovascular and pulmonary diseases from population registers in the Czechia, Poland, and Lithuania. Predictive values of standardised Z-scores of forced expiratory volume measured in 1 s (FEV1), forced vital capacity (FVC), and FEV1 divided by height cubed (FEV1/ht3) were tested. Cox proportional hazards models were used to estimate hazard ratios (HRs) of CVD events of various spirometry indices over the Framingham Risk Score (FRS) model. The model performance was evaluated using Harrell's C-statistics, likelihood ratio tests, and Bayesian information criterion.

Results

All spirometry indices had a strong linear relation with the incidence of CVD events (HR ranged from 1.10 to 1.12 between indices). The model stratified by FEV1/ht3 tertiles had a stronger link with CVD events than FEV1 and FVC. The risk of CVD event for the lowest vs. highest FEV1/ht3 tertile among people with low FRS was higher (HR: 2.35; 95% confidence interval: 1.96-2.81) than among those with high FRS. The addition of spirometry indices showed a small but statistically significant improvement of the FRS model.

Conclusions

The addition of spirometry indices might improve the prediction of incident CVD events particularly in the low-risk group. FEV1/ht3 is a more sensitive predictor compared to other spirometry indices.