Validation of the Korean Genome Epidemiology Study Risk Score to Predict Incident Hypertension in a Large Nationwide Korean Cohort

Prognostic risk models for incident hypertension: A PRISMA systematic review and meta-analysis

OBJECTIVE

Our goal was to review the available literature on prognostic risk prediction for incident hypertension, synthesize performance, and provide suggestions for future work on the topic.

METHODS

A systematic search on PUBMED and Web of Science databases was conducted for studies on prognostic risk prediction models for incident hypertension in generally healthy individuals. Study-quality was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST) checklist. Three-level meta-analyses were used to obtain pooled AUC/C-statistic estimates. Heterogeneity was explored using study and cohort characteristics in meta-regressions.

RESULTS

From 5090 hits, we found 53 eligible studies, and included 47 in meta-analyses. Only four studies were assessed to have results with low risk of bias. Few models had been externally validated, with only the Framingham risk model validated more than thrice. The pooled AUC/C-statistics were 0.82 (0.77-0.86) for machine learning models and 0.78 (0.76-0.80) for traditional models, with high heterogeneity in both groups (I2 > 99%). Intra-class correlations within studies were 60% and 90%, respectively. Follow-up time (P = 0.0405) was significant for ML models and age (P = 0.0271) for traditional models in explaining heterogeneity. Validations of the Framingham risk model had high heterogeneity (I2 > 99%).

CONCLUSION

Overall, the quality of included studies was assessed as poor. AUC/C-statistic were mostly acceptable or good, and higher for ML models than traditional models. High heterogeneity implies large variability in the performance of new risk models. Further, large heterogeneity in validations of the Framingham risk model indicate variability in model performance on new populations. To enable researchers to assess hypertension risk models, we encourage adherence to existing guidelines for reporting and developing risk models, specifically reporting appropriate performance measures. Further, we recommend a stronger focus on validation of models by considering reasonable baseline models and performing external validations of existing models. Hence, developed risk models must be made available for external researchers.

Development of risk models of incident hypertension using machine learning on the HUNT study data

In this study, we aimed to create an 11-year hypertension risk prediction model using data from the Trøndelag Health (HUNT) Study in Norway, involving 17 852 individuals (20-85 years; 38% male; 24% incidence rate) with blood pressure (BP) below the hypertension threshold at baseline (1995-1997). We assessed 18 clinical, behavioral, and socioeconomic features, employing machine learning models such as eXtreme Gradient Boosting (XGBoost), Elastic regression, K-Nearest Neighbor, Support Vector Machines (SVM) and Random Forest. For comparison, we used logistic regression and a decision rule as reference models and validated six external models, with focus on the Framingham risk model. The top-performing models consistently included XGBoost, Elastic regression and SVM. These models efficiently identified hypertension risk, even among individuals with optimal baseline BP (< 120/80 mmHg), although improvement over reference models was modest. The recalibrated Framingham risk model outperformed the reference models, approaching the best-performing ML models. Important features included age, systolic and diastolic BP, body mass index, height, and family history of hypertension. In conclusion, our study demonstrated that linear effects sufficed for a well-performing model. The best models efficiently predicted hypertension risk, even among those with optimal or normal baseline BP, using few features. The recalibrated Framingham risk model proved effective in our cohort.

Development and validation of hypertension prediction models: The Korean Genome and Epidemiology Study_Cardiovascular Disease Association Study (KoGES_CAVAS)

This study aimed to develop and validate the hypertension risk prediction models of the CArdioVascular disease Association Study (CAVAS). Overall, 6,186 participants without hypertension at baseline were randomly divided into derivation and internal validation sets in a 6:4 ratio. We derived two prediction models: the first used the Framingham hypertension risk prediction factors (F-CAVAS-HTN); the second considered additional risk factors identified using stepwise Weibull regression analysis (CAVAS-HTN). These models were externally evaluated among Ansan and Ansung (A&A) participants, and the external validity of the Framingham and A&A prediction models (F-HTN and A&A-HTN) were assessed using the internal validation set of CAVAS. The discrimination, calibration, and net reclassification were determined. During the 4-year follow-up, 777 new cases of hypertension were diagnosed. All four models showed good discrimination (C-statistic ≥ 0.7). Internal calibrations were good for both the coefficient-based and the risk score-based F-CAVAS-HTN models, respectively (Hosmer-Lemeshow chi-square, H-L χ² < 20, P ≥ 0.05). However, the two CAVAS models (H-L χ² ≥ 20, P < 0.05, both) as well as the F-HTN and the A&A-HTN prediction models (H-L χ² = 155.39, P < 0.0001; H-L χ² = 209.72, P < 0.0001, respectively) were not externally calibrated. The F-CAVAS-HTN may be better than models with additional risk factors or derived for another population in the view of the findings of the internal validation in the present study, although future studies to improve the external validity of the F-CAVAS-HTN are needed.

Trend of Prevalence of Atrial Fibrillation and use of Oral Anticoagulation Therapy in Patients With Atrial Fibrillation in South Korea (2002-2013)

BACKGROUND

This study examined the annual prevalence of atrial fibrillation (AF) and its associated comorbidities, as well as the prevalence of warfarin therapy in South Korean patients with AF.

METHODS

The National Health Insurance Service-National Sample Cohort database was searched for subjects aged ≥30 years diagnosed with AF from 2002-2013. The prevalence of AF was analyzed by sex and age, as was the current status of warfarin therapy in AF patients according to CHA₂DS₂-VASc score and comorbidities.

RESULTS

The age-standardized prevalence of AF in men and women was 0.15% and 0.14%, respectively, in 2002, increasing to 0.54% and 0.39%, respectively, in 2013. In 2013, the prevalence of AF in men and women aged 30-39 years was 0.08% and 0.03%, respectively, increasing to 2.35% and 1.71%, respectively, in those in aged ≥60 years. During 2002-2013, the prevalence of AF in men significantly increased among subjects aged ≥30 years and increased in women aged ≥60 years. The age-standardized prevalence of hypertension and diabetes mellitus among AF patients were markedly increased during 2002-2013. Of these AF patients, 86.1% had a CHA₂DS₂-VASc score of ≥2; however, only 39.1% of these were receiving warfarin.

CONCLUSIONS

The age-standardized prevalence of AF increased 2.89-fold over the 12-year study period. The total number of patients with AF in South Korea has been drastically increasing, due to not only aging society but also increasing age-specific prevalence of AF, especially in middle-aged and elderly individuals. The rate of warfarin therapy increased slightly over the study period but remains low.

Recent development of risk-prediction models for incident hypertension: An updated systematic review

BACKGROUND

Hypertension is a leading global health threat and a major cardiovascular disease. Since clinical interventions are effective in delaying the disease progression from prehypertension to hypertension, diagnostic prediction models to identify patient populations at high risk for hypertension are imperative.

METHODS

Both PubMed and Embase databases were searched for eligible reports of either prediction models or risk scores of hypertension. The study data were collected, including risk factors, statistic methods, characteristics of study design and participants, performance measurement, etc.

RESULTS

From the searched literature, 26 studies reporting 48 prediction models were selected. Among them, 20 reports studied the established models using traditional risk factors, such as body mass index (BMI), age, smoking, blood pressure (BP) level, parental history of hypertension, and biochemical factors, whereas 6 reports used genetic risk score (GRS) as the prediction factor. AUC ranged from 0.64 to 0.97, and C-statistic ranged from 60% to 90%.

CONCLUSIONS

The traditional models are still the predominant risk prediction models for hypertension, but recently, more models have begun to incorporate genetic factors as part of their model predictors. However, these genetic predictors need to be well selected. The current reported models have acceptable to good discrimination and calibration ability, but whether the models can be applied in clinical practice still needs more validation and adjustment.